Lab
The projects here share one idea: automate agency routine so there is time for the one thing the client actually sees – the deliverable.
Not a showcase portfolio. These systems run daily in real agency operations, from first concept through architecture to production. The Lab documents tools and workflows; open panel research, methods and data boundaries live separately under Research.
In-house · TypeScript · MCP · Cloudflare Workers · OAuth
The connector makes this data queryable via MCP directly in Claude: one plain-language question instead of a click path through reports. No plan upgrade, on our own infrastructure, read-only.
$230 · plan costs saved per month
In-house · Productive API · Snapshots
Before, that meant pulling data from Productive by hand and checking it against the client budget spreadsheet. Now every client card carries one big number – live from Productive, frozen as a snapshot after the monthly close.
59 clients · 10 team members · one board
Open source · CC BY 4.0 · SKILL.md · Claude · ChatGPT
It walks the agent through the retrieval mechanic of answer engines – chunk, embed, retrieve, ground, cite – and applies it as a repeatable workflow. Two modes: create new content, or rebuild existing pages, baseline first.
Claude / ChatGPT · Agent Skill · CC BY 4.0
Open source · CC BY 4.0 · n8n · OpenRouter · Google Sheets
Every question three times per model, so the stochastic answer becomes signal instead of noise. Detection on regex rather than an LLM judge, so every number stays reproducible. Raw data in Google Sheets, a weekly email report, an alert when the citation rate hits zero – plus an honest reckoning of when the self-build costs more than Peec.ai.
$35 instead of €85 · per month · weekly cadence
Open source · CC BY 4.0 · n8n · OpenRouter · Google Sheets
The workflow separates the two along Simon Willison's dual LLM pattern: the model in control works strictly on enums, counters and IDs and never sees page text; the model that reads page text receives zero company data. Three code gates check without a model, every answer has to cite fact IDs – and nothing publishes itself.
$0.0035 · per page run · injection-hardened
Lab experiment · OKF v0.2 · Gemini 2.5 Flash · RAG
OKF is a directory of Markdown files with YAML frontmatter whose concepts link into a graph. The tool reads your bundle, shows the Concept Library for editing, the knowledge graph with its gaps, and a RAG chat that answers exclusively from your bundle and traces every statement back to its source concept.
Upload → Graph → Chat · OKF v0.2 · Lab experiment
Next step
Which routine eats the most hours in your agency? Write to me – time sinks like these can be eliminated.