Late timesheets delayed accurate client billing for our advertising and marketing agency, so I built a Claude project that reconstructs my week from the tools I already use. It drafts time entries that I review and approve before anything reaches our system. It's useful for anyone who logs time after the fact and loses track of smaller tasks. 1. Before each run, Claude checks that my Chrome browsing history and Claude conversation export, which have no connector, are current. If one is out of date, it reminds me and asks whether to wait or continue without it. 2. It pulls the time I've already entered in the system so nothing gets posted twice. 3. It searches the emails I sent or replied to, my calendar meetings (using Gemini notes to confirm they happened and how long they ran), files I edited in Google Drive, Slack threads I joined, work-related browsing, and Claude work sessions. 4. It builds a timeline for each day and groups related items into one block. An email, a doc edit, and a Slack thread about the same issue count once. Personal activity is left out. 5. It estimates time for each block, rates each estimate as high, moderate, or low confidence, and assigns a project and task using my past entries as a guide. 6. It combines related time by day, project, and task before rounding up to the nearest quarter hour, so small items aren’t each rounded up separately, and writes a short description for each entry. 7. It flags unexplained gaps during my usual working hours and asks me about them. It never fills them in on its own. 8. It checks my calendar for PTO and applies our rules for days I worked anyway, so I post only the leave I actually took. 9. It produces a daily reconstruction, a ready-to-enter timesheet, and a weekly reconciliation, then saves a draft to the project. 10. I correct or confirm entries, and Claude updates the totals. Once I approve, it saves a final version. Entering and submitting are separate commands, and it runs each only when I say so. The project instructions require Claude never to invent work or pad hours, never to double-count, and to disclose any source it couldn’t search. Instead of trying to remember my week, I now review entries that already have project codes and descriptions, and it also surfaces work I had forgotten.

I use Claude as an SEO helper for my WP site. It reads my search performance data and suggests improvements, so I don't have to dig through the numbers myself. This is useful for anyone who runs a website and wants to improve it using their own search results. 1. Connect your WP site to Search Console. 2. Let Claude read the Search Console results. 3. Ask Claude to improve the content. 4. Let Claude make the improvements. 5. Republish the updated content on your site. The result is improved content for your WP site, based on what your search results actually show.

I built a set of agents that run every day to find local businesses with no website, build a site for a selected business, and email the mockup to that lead. It's for anyone who sells web services to local businesses and wants to automate the prospecting. 1. Each day, my Gemini and ChatGPT agents check the major cities in the state I select, for the industry I select, and find the best businesses that don't have a website. They add those businesses to a spreadsheet. 2. A second agent reads the spreadsheet, selects the best prospect based on its need for web services and likelihood of buying, and starts building its website. 3. That agent checks the business's social media for images and its Google Business Profile for information. It also looks for a logo. If there isn't one, it creates a logo for them. 4. The agent finishes building the website, which becomes the mockup. 5. A third agent takes the mockup and sends an email with it to the lead. 6. A fourth agent is set up to reply once the lead responds, book them on a call, and put the call on the calendar. The result is a workflow that takes selected businesses from a prospect spreadsheet through a website mockup and follow-up, with replies leading to a booked call.

I use AI to turn a single product into ads, social media posts, and short promotional videos for my business. This is for anyone who needs to promote a product across several channels without spending hours on each one. 1. I give the AI the name or a picture of the product I want to advertise. 2. The AI studies the product and creates an attractive advertisement. 3. It writes catchy promotional captions and sales descriptions. 4. It generates creative designs and promotional images for social media. 5. It creates short video scripts and video-generation prompts. 6. I review all of the content and make any changes that are necessary. 7. I publish the finished content on WhatsApp, Facebook, Instagram, and TikTok. This workflow saves me time, improves my marketing, and helps me attract more customers.

I use Claude, connected live to Airtable through MCP, as a one-person GTM team. It runs a daily pipeline war room, drafts outreach, and helps me create data-driven LinkedIn content. The workflow uses Claude, Airtable with a Prospects table and a LinkedIn Posts table, an outbound email platform for sequences, and LinkedIn. I review everything before sending or publishing, so a human stays in the loop on anything that goes out under my name. Step-by-step: 1. I start a morning war room session by opening Claude and letting it read my live Airtable pipeline. It gives me a scoreboard of what moved, what is stuck, and who needs a touch that day, along with a quick drill on my pitch. 2. Claude flags unworked contacts and suggests the next action for each. It drafts outreach using a written style rulebook: peer tone, hypothesis framing, short sentences, and no brochure language. I review everything and send it myself. 3. I log every LinkedIn post in Airtable with its full text, followed by its analytics: impressions, industry mix, seniority, comments, and notes on what worked. 4. Before writing a new post, Claude reviews the full post history, ranks the posts, and identifies which patterns drove reach and engagement from my target audience. 5. When I learn a new framework, such as Eugene Schwartz’s five stages of market sophistication, I give it to Claude along with my post history. Claude diagnoses where my content is going wrong and drafts a post designed to fix the pattern. 6. I publish at 7:30 AM, and a colleague seeds a comment during the first 30 minutes. Claude then logs the post back into Airtable, closing the loop for the next post. Key prompt: “Read every post in my LinkedIn Posts table. Rank them by impressions and ICP engagement. Tell me what the top performers have in common and what the weak ones share. Then apply [framework] and draft one post that fixes the pattern. Follow my style rules. Flag any claim or statistic you can’t verify.” What makes this work is that the analytics live in the same table as the content, so every post makes the next one smarter.

I connected ChatGPT to Metricool to get more personalized analytics on how our social media is performing. This workflow is for anyone who manages social channels and wants to see which posts work best on each platform before writing the next batch. Step-by-step: 1. I connected ChatGPT to my Metricool account. 2. I used ChatGPT to analyze social media performance, including which posts were performing best on each platform. 3. I used those results to develop better-performing posts for each platform. 4. Once ChatGPT was trained on my style and content calendar, I automated it to create and schedule posts at optimal times.

As an agency, we have to report the work we do for our clients and how efficient it is. Building these presentations by hand is very time consuming and boring, and there is little value in making them. At Le Trefle à 5 Feuilles we decided to automate this recurring task. Before, it took about 3 hours to gather every stats report, make the presentation available to the client, and interpret the stats and recommend further actions. I keep a human in the loop, because someone has to read the report before it is sent. Since we work in Google Workspace, I built the workflow with several Gemini Gems: 1. Google Apps Script watches one folder on Google Drive and detects when a new statistics report is posted. 2. The first Gem decodes the report and inserts the variables into it. 3. The second Gem interprets and sums up all the statistics. 4. The third Gem merges those statistics into the template the workflow calculated. 5. I review the finished presentation before sending it to the client. It now takes only 3 minutes to produce the report, so the consultant can focus on the real value: their analysis of the campaign.

I make content—posts, articles, and videos—and it brings people to my site. But most visitors would skim for 30 seconds and leave, and nobody used my contact form. So I built an AI version of myself. I trained it on my own content, including my posts, articles, notes, knowledge, and the way I explain things. It learned not only what I know, but also how I talk and think. Now it lives on my site and chats with visitors in my voice. As it chats, it identifies who’s a real lead and sends those people to me with the full story. Visitors can ask questions, get answers in my voice, and follow up as deeply as they want. Step-by-step: 1. I collected my content, posts, articles, notes, knowledge, and explanations. 2. I trained an AI version of myself on that material, including how I talk and think. 3. I created a link and placed the AI on my site. 4. Visitors ask questions and receive answers in my voice. 5. The AI identifies real leads and sends them to me with the full conversation and context.

Yesterday, I built a social media workflow in Awish for a business that wanted to post more consistently without managing three platforms manually. The idea was simple: let Awish understand the business first, then use that context to plan different content for Instagram, LinkedIn, and X instead of reposting the same thing everywhere. I built the entire workflow by describing what I wanted in the Awish chat. Step-by-step: 1. I opened Awish and wrote: “Analyze this business from its website. Based on what the company does, its audience, products, and positioning, create separate content plans for Instagram, LinkedIn, and X. Generate the posts, publish them automatically at the times I choose, analyze how each post performs, and send me the important insights on WhatsApp. I also want to be able to manage the workflow from WhatsApp.” 2. Awish analyzed the website, understood the business, and planned the complete content workflow. 3. I connected the company’s Instagram, LinkedIn, X, and WhatsApp accounts and approved the plan. 4. Awish created a different content strategy for each platform instead of copying the same post everywhere: more visual content for Instagram, business-focused posts for LinkedIn, and shorter, conversation-driven posts for X. 5. I chose the publishing schedule, and Awish started creating and publishing the posts automatically at those times. 6. After publishing, Awish tracked performance and analyzed which topics, formats, and messages were getting the strongest response on each platform. 7. Awish sent me short WhatsApp updates with the important insights, such as which post performed best, what topic was gaining traction, and what it recommended changing next. 8. I could also manage the automation directly from WhatsApp by asking what was scheduled, changing a publishing time, requesting another post, pausing publishing, or asking for the latest performance summary without opening Awish. The useful part for me is that this is not just automatic posting. The workflow starts by understanding the business, treats each social platform differently, learns from what gets published, and keeps the whole process manageable from WhatsApp.

Content Repurposing System: one transcript into 4 platform-ready posts in 18 seconds. THE PROBLEM Every video cost me two hours turning it into posts for Twitter/X, LinkedIn, Skool and Instagram. The writing wasn't hard. The context switching was. Four platforms, four tones, the same idea rewritten four times. Built during the Skool x Hostinger n8n hackathon, Dec 2025. Still my daily workflow. STACK: n8n on a Hostinger VPS, OpenAI, Google Sheets. 13 nodes. HOW TO BUILD IT Manual Trigger. Swap for a Form or Drive trigger if you want it hands-off. Set node "Set Transcript", one string field: transcript. Leave a real sample transcript in the default value so anyone can hit execute and see output immediately. IF node "Check Transcript", two conditions with AND: transcript is not empty, and {{ $json.transcript.length }} > 50. False branch goes to a Stop and Error node. Four minutes of work. It's why I've never burned 5 API calls on a blank field. OpenAI node "Analyze Content", model gpt-5.4-mini, Simplify Output OFF: You are a content analyst. Analyze this video transcript and extract: Main topic/theme 3-5 key insights or takeaways Target audience Tone (educational, motivational, technical, etc.) Any specific examples, statistics, or stories mentioned Transcript: {{ $json.transcript }} Provide your analysis in a structured format. I don't send the transcript to four writers. I send it to one analyst first, and all four writers read that analysis. This lifted quality more than any prompt tweak: the posts share one reading of the material instead of each model guessing. The stronger model goes here for the same reason. Wrong analysis, four wrong posts. 5-8. Four generators, all gpt-4o-mini, Simplify Output OFF, all wired from Analyze Content's single output. Each pulls the same two inputs: Content Analysis: {{ $('Analyze Content').item.json.choices[0].message.content }} Original Transcript: {{ $('Set Transcript').item.json.transcript }} Then its own rules. Twitter (temp 0.8): hard hook, under 280 chars, one insight, no hashtags. LinkedIn (0.7): 150-250 words, 2-3 line paragraphs, ends on a question, no hashtags. Skool (0.8): 100-200 words, always a numbered list of actionable takeaways, ends by inviting replies. Instagram (0.8): 125-175 words, 5-8 hashtags, plus a detailed "Visual suggestion:" for a designer or image model. LinkedIn needed a tone block after v1 read like a press release: talk like you're with a colleague over coffee, use I and you, never "leverage", "in today's landscape", "fast-paced". Naming banned words works. "Write conversationally" does nothing. Merge node "Collect All Posts", 4 inputs, one generator per index. Aggregate node, mode All Item Data. Puts all four posts on one row instead of four. Code node "Format Output". Reads each generator by node name, each in its own try/catch, so one failure still writes a row. Builds a readable timestamp, a 100-character transcript_preview, and status: 'Generated'. Google Sheets, Append Row, Map Automatically. THE SHEET Seven columns, headers in row 1, named to match the Code node exactly: timestamp, transcript_preview, twitter_post, linkedin_post, skool_post, instagram_post, status. Status is a dropdown: Generated > Reviewed > Scheduled > Published. The system drafts, I decide. FOUR THINGS THAT COST ME HOURS Turn Simplify Output OFF on every OpenAI node. Every expression reads choices[0].message.content, which only exists in the raw response. Leave Simplify on and you get four empty columns with no error explaining why. No title row above your headers. I had a merged title in row 1, headers in row 2. Map Automatically stopped seeing my columns and silently built duplicates beside them. Extend data validation down the whole column (G2:G1000, not G2). I set the dropdown on one cell and every appended row arrived as plain text. Kill markdown in the prompt, not after. I wasted an evening regex-stripping ** in the Code node. The fix was upstream: tell Skool and Instagram plain text only, CAPITALS or "quotes" for emphasis. Zero artefacts since. Post-processing cleanup means your prompt is underspecified. RESULT Two hours per piece became 18 seconds of runtime plus 5-10 minutes of review. I tested 20 transcripts across five content types (tutorial, interview, news, explainer, motivational). Most were publishable with light edits. The failure mode never changed: rambling transcript, vague analysis, four vague posts. Which is exactly why the analyst node gets the better model. Budget 30 minutes to rebuild. The prompts are the product. Copy the structure, then rewrite the platform rules in your own voice. That's what decides whether it sounds like you or like everyone else.

Organic social content is one of the best sources of ideas for ads, so I built a workflow that finds short-form videos performing well in my niches, analyzes why they work, and rewrites the strongest hooks for my brand. Apify scrapes Instagram Reels by hashtag and TikTok videos by keyword across three niches: AI, productivity, and career growth. The workflow filters for English-language videos posted within the last 15 days that are 15–90 seconds long and have more than 50,000 plays. It then ranks them by engagement rate rather than views alone. A simple log file tracks every video I’ve already analyzed, so the workflow doesn’t process the same video twice. ElevenLabs transcribes each video’s audio. Claude then extracts the exact opening line, identifies the hook formula and video structure, and writes a version of the hook for my brand. Everything is compiled into one dated document with the top three discoveries, the strongest hook from the run, and any new patterns I haven’t tried yet. With one command—"Run research"—I get about 20 proven hooks and video structures to test in ads for less than $1 per run. Step-by-step: 1. I use Apify to scrape Instagram Reels by hashtag and TikTok videos by keyword across the AI, productivity, and career growth niches. 2. I filter the results for English-language videos posted within the last 15 days, 15–90 seconds long, with more than 50,000 plays. 3. I rank the remaining videos by engagement rate instead of views alone. 4. I check a log file to skip videos I’ve already analyzed. 5. I use ElevenLabs to transcribe each video’s audio. 6. I ask Claude to extract each video’s exact opening line, hook formula, and structure, then rewrite the hook for my brand. 7. I compile the results into one dated document with the top three discoveries, the strongest hook from the run, and new patterns to test. 8. I run the workflow with the command "Run research" to generate about 20 hooks and video structures for ad testing at a cost of less than $1 per run.

I turned tedious Google Business Profile spammer tracking into a Claude Skill. It organizes the research and puts all findings into an XLS file that can be submitted through the Google Business Redressal form and the GBP forum for escalation by a Google Product Expert for Google review. Step-by-step: 1. I created a list of suspected spam profiles with each business name and Google Maps URL. 2. I asked Claude to examine each profile, determine its website, and identify any relationships between the domains. 3. I asked Claude to identify other businesses operating at the listed addresses. 4. I asked Claude to determine whether each profile is listed with the country’s primary Google data provider or providers. 5. I asked Claude to determine whether each profile is listed in a state or government registry. 6. I asked Claude to analyze commonalities across the profiles’ reviews, descriptions, and photos. 7. I asked Claude to identify patterns indicating whether the profiles are fake or real and whether they are related in some way. 8. I had Claude compile all findings into an XLS file for submission through the Google Business Redressal form and the GBP forum.

I use Claude Desktop on my Mac, connected to Canva and Metricool, to build and schedule social media posts. I used ChatGPT to help me set everything up because it has more history and access to my company knowledge documents. ChatGPT created instruction files for Claude that provide our company context and guidelines. I pointed Claude to our website, which contains many articles, and connected our Canva and Metricool accounts. We discuss suitable topics to post about. Claude reviews the website for relevant articles or landing pages to link to, then suggests a series of Facebook and Instagram posts. It checks the designs in our Canva account, adjusts them as needed, or asks me for photos and other artwork. Claude then builds the posts in Metricool and saves them as drafts for me to review, following our working rules. I review the drafts and move them to pending. Claude checks that they will publish automatically on the correct date and at the correct time, and it creates links with meaningful UTM parameters. After publishing, I can ask Claude to analyze the results, identify what is working and resonating with my market, and help us test different approaches, content, and topics. Metricool captures the data, and Claude uses it to inform the next round of posts. This saves me hours every week, gives me time to work on other things while Claude handles the process, and produces results that are improving each week. Step-by-step: 1. I used ChatGPT to help configure Claude Desktop and create instruction files containing our company context and guidelines. 2. I connected Claude to our website, Canva account, and Metricool account. 3. I discuss potential topics with Claude, and it finds relevant website articles or landing pages to link to. 4. Claude suggests a series of posts for Facebook and Instagram. 5. Claude reviews our Canva designs, adjusts them when necessary, or asks me for photos and other artwork. 6. Claude builds the posts in Metricool and saves them as drafts for me to review according to our working rules. 7. I review the drafts and move them to pending. 8. Claude checks the publishing date and time and creates links with meaningful UTM parameters. 9. After publication, I ask Claude to analyze the results and identify what is resonating with my market. 10. I use the Metricool data and Claude’s analysis to test different approaches, content, and topics in the next round of posts.

I use Claude Cowork and Meta MCP to map my existing ad creative data and find winning combinations. Once the data is mapped, I can usually identify one concept that wins more often than the others, has absorbed more spend, and still maintains an efficient CPA. That is the winning concept, and it is where I should focus 60% to 80% of my production time. Step-by-step: 1. I connect Claude Cowork to Meta MCP and Google Drive. 2. I place the brief for every ad I published in the past 365 days into one Google Drive folder. Each brief includes the script, format, offer, and persona it was written for. 3. I prompt Claude to work through the Drive folder and build a spreadsheet tagging every ad by persona, angle, offer, and format. 4. I prompt Claude to pull each ad’s spend and CPA through Meta MCP and add those metrics to the spreadsheet. 5. I ask Claude to turn the spreadsheet into a flowchart in which persona branches into angle, angle branches into offer, and offer branches into format. Each branch includes its spend and CPA. After the data is mapped, I use the flowchart to identify the winning concept and prioritize it in production.

I asked ChatGPT to create a graphic for my company. I provided our company colors, logo, brand guide, the objective of the graphic, and information about our audience. ChatGPT then created the graphic based on those details. Step-by-step: 1. I asked ChatGPT to create a graphic for my company. 2. I provided our company colors, logo, and brand guide. 3. I explained the objective of the graphic. 4. I described the intended audience. 5. ChatGPT created the graphic using the information I provided.

I built an AI workflow to automate guest-posting outreach. I use Claude to analyze target website requirements, draft personalized pitch emails for editors, and optimize my responses so I can pursue high-quality backlinks more efficiently. Step-by-step: 1. I provide Claude with the requirements for each target website. 2. I use Claude to analyze those requirements and identify what to address in the outreach. 3. I ask Claude to draft a personalized pitch email for the editor. 4. I use Claude to optimize my responses during the outreach process.

As a business owner, I used to check performance data across Google Analytics 4, Google Search Console, and Google Merchant Center by logging into three separate portals, navigating complex submenus, and exporting raw CSVs. To solve this, I built an automated workflow that connects my AI coding assistant, Google Antigravity, directly to all three Google platforms through a Google Cloud Service Account. Instead of manually clicking through dashboards, I can ask natural-language questions in plain English, such as "Did yesterday's email send generate traffic or phone bookings?" or "Are any products disapproved in Google Merchant Center?" I then receive instant, cross-platform analysis in seconds. Step-by-step: 1. I created a Google Cloud Service Account by going to Google Cloud Console (console.cloud.google.com) > IAM & Admin > Service Accounts > Create Service Account. I named it `ai-marketing-assistant`, copied the generated service account email address, such as `ai-marketing-assistant@<project-id>.iam.gserviceaccount.com`, and downloaded the JSON private key file to my local project folder. 2. In Google Cloud Console > APIs & Services > Library, I enabled the three required APIs: - Google Analytics Data API - Google Search Console API - Content API for Shopping (Google Merchant Center) 3. In Google Analytics > Admin > Property Access Management, I added the Service Account email address with "Viewer" permissions and copied my numerical GA4 Property ID. 4. In Google Search Console > Settings > Users and permissions > Add User, I added the Service Account email address with "Full" or "Restricted" access. 5. In Google Merchant Center > Settings & Tools > Account Access > Add User, I added the Service Account email address with "Standard" or "Admin" access and ensured that "Content API access" was enabled. 6. In my local AI environment, such as Google Antigravity or a custom Python environment, I authenticated using standard Google client libraries (`google-oauth2`, `googleapiclient`, `google-analytics-data`) connected to the downloaded JSON key file. 7. Anytime I launch a marketing campaign, want an SEO audit, or need to check product feed health, I ask my AI assistant a plain-English question. 8. The AI executes live API queries against GA4, Search Console, and Merchant Center, cross-references website traffic with bookings, and delivers an instant report.

I connected Claude Code to Apify's API to scrape high-performing content from IG/TikTok for ad creative inspiration, and to ElevenLabs' API to automatically transcribe videos — so I can analyze not just visuals, but the exact hooks, pacing, and language top creators are using. From there, I developed a scriptwriting system that takes rough thoughts on a hook and angle and turns them into ad scripts, drawing inspiration from winners and applying proven copywriting principles. After generating, it also grades itself against a 12-point rubric. If it doesn't score at least 90%, it rewrites until it does. I then feed it back in and say, "This is the final version." It analyzes the changes I made and updates its understanding of my style. Step-by-step: 1. I connected Claude Code to Apify’s API for collecting high-performing Instagram and TikTok content. 2. I connected ElevenLabs’ API so the workflow could automatically transcribe each video. 3. I analyzed the winning examples for their hooks, pacing, visual patterns, and exact language. 4. I fed the system a rough hook and angle and had it draft ad scripts using those proven patterns. 5. I created a 12-point grading rubric and required a rewrite whenever a script scored below 90%. 6. After making my own final edits, I fed the approved version back into the system so it could learn my style.

I run an out-of-home advertising agency in Malta, covering billboards, buses, hotel screens, and radio. Our entire business ran on Monday.com boards for CRM, deals, bookings, supplier bills, and bus-campaign reconciliation. The system was expensive, difficult to change, and full of broken formulas. I’m not a developer, but in about two weeks I worked with Claude to replace it with our own CRM built on Google Sheets and Google Apps Script. The team now uses it every day. Step-by-step: 1. I mapped our real processes first, explaining in plain language how we sell, book, invoice, and pay partners. Claude read our existing Monday.com boards and imported the data. 2. I built the system screen by screen, releasing each part and testing it with live data before moving on. The CRM now includes contacts, companies, deals with order lines, bookings, billing, partners, tasks, and a dashboard. 3. I automated repetitive tasks. When I upload a signed order form, the app reads the lines. Bookings are created automatically from deals, and a Gmail side panel and shared mailbox file client emails under the correct contact or deal. 4. I connected QuickBooks Online. The system pulls invoices and supplier bills, calculates each partner’s revenue share according to its own rules, produces the monthly partner report, and creates the bill. I approve anything that writes to the accounts. 5. I turned a monthly spreadsheet chore into an automatic check for bus campaigns. The app compares what we committed to the client with what the bus operator billed us and flags overbilling or margin problems month by month. The first run found a supplier bill that appeared to be a duplicate. 6. I made the system safe to hand over. Every change is logged and can be undone, with user roles and a shared drive in place. We also wrote a short user guide and test checklist before the team started using it. The main lesson I learned was to treat AI like a capable builder who needs your business rules spelled out. Starting with real data, releasing small pieces, and checking each one before adding the next made the build manageable. The tools I used were Claude, Google Sheets, Google Apps Script, Gmail, and QuickBooks Online.

I built an autonomous, end-to-end AI Sales Development Representative (SDR) engine entirely in n8n. On a scheduled trigger, the agent calculates targeting parameters, reads long-term CRM memory to avoid duplicate outreach, searches for and qualifies prospective leads, scrapes company websites for buying signals, drafts tailored outreach emails, writes structured relational data to PostgreSQL, and reports execution summaries through Telegram—with zero manual intervention. The system is currently deployed in production for a B2B agricultural export business, generating qualified international wholesale leads on a recurring schedule. Most AI automations rely on simple linear scripts or break down when handling complex agentic tool workflows. This system addresses three common failure points: - High API costs: Re-sending large system prompts and tool schemas on every agent iteration drains tokens. - Context blindness: Agents without memory of previous contacts can send duplicate outreach. - Database crashes: Agents may hallucinate ENUM values or fail to insert nested one-to-many arrays into relational tables. The workflow uses a Cloudflare-proxied Claude Sonnet 4.6 model with prompt caching, persistent CRM memory reads, and a fault-tolerant parallel database-write architecture. The stack includes n8n as the orchestrator; Claude Sonnet 4.6 through a Cloudflare Worker proxy as the LLM core with ephemeral prompt caching; PostgreSQL for CRM contacts, intelligence, and outreach tables with custom ENUMs; SerpAPI for prospect discovery; Firecrawl for website content extraction; and Telegram for execution reporting. The workflow exposes these tools to the n8n agent: - `read_relationship_memory`: Read-only SQL access to historical contact and outreach data, preventing duplicate prospecting. - `Lead_Finder`: Searches for and identifies target prospects by country and sector. - `Scrape_Website_Content`: Extracts website content, buyer-intent signals, and objections from discovered domains. - `write_relationship_memory`: Writes leads, intelligence facts, and drafted emails to Postgres in one resilient call. Step-by-step: 1. A Schedule Trigger feeds a JavaScript “Country Calculator” node that resolves the day’s targeting parameters—region and industry focus—using ISO week rotation. This cycles outreach across markets automatically. 2. The AI Agent connects to an OpenAI Chat Model node whose Base URL points to a custom Cloudflare Worker. The worker translates OpenAI-formatted requests into Anthropic’s Messages API, enabling Claude Sonnet 4.6 while injecting ephemeral cache-control headers into the system prompt and tool definitions to reduce repeat-token costs. 3. Before researching, the agent calls `read_relationship_memory` to check relationship status and outreach history, preventing duplicate contact attempts. 4. `Lead_Finder` searches target sectors in the day’s region and returns seven filtered candidates. `Scrape_Website_Content` then visits each domain, extracts clean page text, and surfaces offerings, value propositions, and likely objections. 5. The workflow writes nested one-to-many data—multiple facts and one outreach log per contact—without item duplication or ENUM crashes. The tool schema requires a strict JSON array with exact ENUM string choices spelled out in the description. 6. A sub-workflow triggered by “When Executed by Another Workflow” splits the array, then flattens nested `contact.*` fields to root keys using JavaScript. 7. An upsert query, `ON CONFLICT (email) DO UPDATE`, writes the contact, increments `email_count` for repeats, and returns `contact_id`. 8. A “Re-attach Context” node merges `contact_id` back with the original intelligence array and outreach payload because n8n strips extra data through single-row database nodes. 9. Two parallel branches run: one inserts the outreach log with `ON CONFLICT DO NOTHING`, while the other splits and inserts each intelligence fact with defensive ENUM sanitization. This eliminates crashes and duplicate rows during retries. 10. The agent’s final output triggers a Telegram message summarizing the discovered leads, extracted facts, and drafted emails, sent directly to the operator’s phone. The result is a production-grade, self-healing AI outbound pipeline running with zero manual intervention. It maintains CRM data integrity, avoids duplicate outreach, and uses prompt caching to keep LLM costs low at scale.