5 notes
Software engineering
Posts filed under Software engineering, newest first.
Year 2026
- An agent's context: client knowledge, memory and permissionsNote4 min readThe agent explores the code on its own. Refining its context means bringing it what it can't find: knowledge of the client, a memory of its sessions and permissions around them, calibrated to confidentiality and compliance.
- A minimal harness: reuse what exists, keep the agent in checkNote4 min readMapping all development know-how into skills costs more than it returns. I reuse what exists, write only the high-value skills, and the harness is mainly there to keep the agent in check: permissions, tests, oversight.
- One model per role, with just enough intelligenceNote4 min readSpec-driven development with less human in the loop: each step becomes a role, served by the minimum intelligence that does the job. The developer becomes product owner and settles early who validates what.
- Client data and LLMs: protect, verify, choose where inference runsNote4 min readData protection starts as soon as you write the system that processes it. You can stay compliant with a capable model if what the LLM does is verifiable; a proxy centralises costs, anonymisation and keys.
- Running an unknown repo without exposing your machineNote4 min readFake technical tests are a documented attack. Two settings limit the damage; the rest takes an isolated environment, with no secrets, even disposable, whose configuration comes from you and not from the repo.