
Claude Certified Developer, Foundations
Anthropic certification for building, integrating and shipping production applications and agents on Claude: the Claude API, Claude Code, custom tools and MCP servers. Earned September 2026.
I build AI systems around real work, test what they do, and help teams operate and improve them.


Anthropic certification for building, integrating and shipping production applications and agents on Claude: the Claude API, Claude Code, custom tools and MCP servers. Earned September 2026.
Select Services Partner in the Claude Partner Network.
Intent Solutions connects that engineering to evidence, teaching, open source, and products.
Shipped and running: the projects, with live GitHub stars.
Live
Open-source skills marketplace ยท about 56K Skills.sh installs (Oct 2026)
Live
Financial modeling skills for Claude Code: DCF, LBO, variance, pivots
Live
Reads and safely edits DXF and vector PDF drawings for AEC teams
Live
Slack-native governance for Claude Code: policy-checked tools, signed audit log
Live
Dashboard + TUI for monitoring agent swarms in real-time
Live
The first Intent Agent Model runtime, on Google ADK (historical V1)
Live
The team's memory keeper: admits by code, keeps tamper-evident receipts
Live
Plain English in, a TimeGPT forecast pipeline out, inside Claude Code
Upstream, not just downstream: work accepted by outside maintainers.
51 merged PRs
Across 18 external repos.
Authored by Jeremy and accepted by outside maintainers. Contribution does not imply employment, partnership, or client status.
| Project | What was merged | Stack | Merged PRs |
|---|---|---|---|
| NOW LMS | i18n compile-at-boot fixes, enrollment integrity constraints, theme perf, and test coverage for the open-source learning management system | Python, Flask, i18n | 14 |
| Kobiton Automate | Mobile device-cloud test automation contributions | Automation, Testing | 10 |
| Blur Extension | Teams, Slack, export/import, custom patterns | JavaScript, Privacy | 4 |
| Beads | Natural-language skill activation and core fixes | Go, Claude-Code | 2 |
| PostHog | React state management and feature-flag bug fixes | TypeScript, React | 2 |
| Kilo Code | Agent runtime test fix | TypeScript | 1 |
| tldraw | Prettier extension fix | TypeScript | 1 |
| Filament | Dark mode fix | PHP, Laravel | 1 |
| Vertex AI Samples | ADK inline-source deployment tutorial for Agent Engine | Python, Vertex-AI, ADK | 1 |
| Agent Starter Pack | Bob's Brain production ADK reference in the community showcase | Docs, ADK | 1 |
Also merged in cord-cutter, OmaSafe, agent-brain, xireactor-brilliant, wasteland, claude-skills-collection, awesome-agent-skills and cx-core.
The stack behind everything on this page. No affiliate links, just what survives daily use.
Build logs and field notes from startaitools.com.
If you quote, benchmark or budget an open-weight model by one price per model, one number is standing in for a spread of sellers and serving precisions. This post shows how wide th...
If you publish numbers computed from a feed you are not cleared to redistribute, the public output can leak the feed without anyone deciding it should. The usual cause is a publish...
If you run a knowledge base or RAG store where new entries pass a policy check before an indexer picks them up, a “success” from the write step does not prove anyone ca...
How do I check if a cron job is already running without matching your own job? Walk /proc for your own ancestors before you call a collision. Build the chain up from the shell that...
Three of our checks gave the wrong answer on the same day, and one rule fixes all three: a check has to say what it looked at, and what it looked at has to be the real thing. A che...
A scheduled multi-agent writing pipeline runs against a 45-minute wall-clock ceiling, and this post hands you the three numbers worth measuring, the reason shrinking each request d...