I write about system design, engineering decisions, and lessons from building real products. Some pieces are complete guides. Others are shorter notes that I will keep improving over time.
Part 2 of building an AI harness around TalonHR in Go: the execution loop, tool registry, state, approvals, partial failures and testing. Most of the real work is making the software around the model predictable.
Notes from building an AI harness around TalonHR in Go: tool discovery, the agent loop, auth, context, approvals and failure handling. Turns out the language model is only one small part of the problem.
Kenya celebrates its startup funding headlines, but early-stage founders face compliance, capital and procurement barriers built for mature companies. Regulation should scale with risk and size, giving young businesses room to try and fail.
Talon had the jobs, but job seekers weren't sticking around. So we asked them why. The answer: we'd built too much. Here's what we cut, what we changed, and what 24 new sign-ups taught us about doing less.
Three weeks into Talon, the jobs are there, employers and recruiters are joining, but job seekers have been surprisingly slow to follow. We started asking why, and what we’re learning is changing how we think about the problem Talon needs to solve.
Discover how Talon built a production-grade Model Context Protocol (MCP) service to seamlessly connect AI agents with hiring workflows while strictly preserving identity, permission, and workspace boundaries.