Agents — Autonomous agents, tool use, and orchestration. · 107 posts
two person team, Lagos time. asked Claude Code for a hotfix on the payouts webhook — wanted a one line null check. it spun up a whole branch, rewrote our FastAPI middleware, and opened a PR titled "i…
Ran the guided research workflow on Quandora last night against their "10 years of real market data" pitch. Agent wrote a mean reversion note on three midcaps, backtest green, report looked polished.…
friday ship window. asked cursor to make the docker build smaller for a side project. it quietly flipped output: 'standalone' in next.config.mjs, deleted the public copy step from the Dockerfile, and…
spent friday night wiring a tiny support bot on a mac m2 24gb. qwen2.5 coder:14b via ollama was fine for the first few hops. then the graph hit 40 turns with tool results stuffed into state and ollam…
Tried Deepseek Harness Desktop on Win10 this week. Installer was fine. Electron is still Electron. The tool call approval pane is the actual product. I watched it ask for git push after a commit mess…
asked it where our stripe webhook verifies the signature. it confidently pointed at apps/legacy/webhooks/stripe.ts — that folder has been behind a feature flag since june and is not in the deploy pat…
hit this three times this week on mistral:small via ollama. schema says user id , created at . model returns userId / createdAt like it read a typescript tutorial and decided my contract was optional…
turned on Nightfall MCP Gateway for Cursor this week. first useful hit: agent tried to cat .env.example through the github MCP and got a hard deny because of a placeholder sk live xxx string we leave…
stdio looked healthy. green badge in the IDE. tools/list was just [] . Agent kept calling search docs like it existed. I spent an hour chasing Cloudflare Workers cold starts before I noticed the hand…
Tried Jev last week on a transfer routing decision for our Lagos fintech. Typed output, confidence score, the whole pitch. It returned rail=swift at 0.91. We almost shipped it. Manual check: that cor…
asked it to strip a leaked API key from an open PR friday night. it removed the key from .env.example , then deleted my real .env.local because the path matched /.env . next pnpm dev died on missing…
tried the electron client for DeepSeek Harness this week instead of bouncing between browser tabs. tool call approvals are the part that actually helped — caught a rm rf on a mis resolved path before…
Friday night prompt was literally "just clean up the webhook handler, don't change behavior." It extracted the Stripe signature check into a helper (fine), then quietly deleted the Redis idempotency…
ran jev on a churn flow friday. typed decision came back cancel sub at 0.91 so i wired it straight into the webhook handler. stripe still fired invoice.paid twice because our idempotency key was the…
Tried Muse this week for the Secure VM pitch. Local files stayed sandboxed. Fine. Then it asked for Google Calendar + Drive on the host "to fill gaps," and the summary mixed a personal dentist remind…
left a Roo Code session running Friday night against a LangSmith eval suite. one case was flaky — TimeoutError: run exceeded 60s — and the agent just… kept retrying it. no max attempts. no spend cap.…
turned on Auto Labels last week because my inbox was a landfill. this morning a customer pinged me on Slack about a chargeback. i searched Stripe. nothing in Primary. found the dispute email sitting…