Ochat – reproducible, diffable LLM workflows in a single Markdown file
I built Ochat, a toolkit for building AI agent workflows out of a small set of primitives. The core primitive is ChatMarkdown (ChatMD): a single .md file is both: the prompt/program (model config, tool allowlist, instructions, context), and the auditable transcript (assistant replies + tool calls + tool outputs) The part that feels most powerful in practice is that this simple building block scales: with good prompting + a curated tool set you can build lots of workflows, and then package them a
Read original source
Source record
Recorded metrics
points · 1 votes
2026-11-06 22:15:18.868Z
cumulative since publication
Research analysis
Reported problem
Source account: I built Ochat, a toolkit for building AI agent workflows out of a small set of primitives. The core primitive is ChatMarkdown (ChatMD): a single .md file is both: the prompt/program (model config, tool allowlist, instructions, context), and the auditable transcript (assistant replies + tool calls + tool outputs) The part that feels most powerful in practice is that this simple building block scales: with good prompting + a curated tool set you can build lots of workflows, and then package them a
Frequency & alternatives
Recorded author: dakotamurphyucf. Source votes: 1 votes (Nov 6, 2026 UTC; cumulative since publication); previous same-scope observation: 1 (Nov 6, 2026 UTC). These observations do not establish demand growth. Recent records to compare: “Ask HN: Is anyone running multi/always-on agents that don't cost a fortune?” (Hacker News, Nov 6, 2026); “Ask HN: Engineers Focus Using AI” (Hacker News, Nov 6, 2026). Shared themes are navigation hints; they have not been verified as the same need or independent corroboration.
Demand hypothesis
Treat the reported task or obstacle as an interview lead. A feature request, complaint or search for alternatives does not by itself identify a budget owner or willingness to pay.
Commercial evidence gaps
Missing evidence: distinct affected users, repeated occasions, current workaround, measured time or money cost, purchasing authority and a response to a concrete offer.
Validation decision
Group original reports by the same task and deduplicate authors and reposts. Ask how the task is handled today and what it costs; test a defined offer before claiming paid demand.