Prior authorization is an evidence workflow
A synthetic workbench follows a missing record through request, reassessment and human review, with precise limits on what its agent can decide.
4 min read
blog.md
Blog
Writing by Subodh Jena on software engineering, LLMs, agent workflows, and the decisions behind building products.
What I would measure before shipping an AI workflow
A practical release evaluation that checks outcomes, authority, repeated runs, latency, and cost. Includes a small harness that exposes a misleading improvement.
8 min read
Field service readiness expires
A field-service workbench that checks parts, people and access before a visit, and withdraws approval when its supporting evidence changes.
4 min read
Tool calls that can be retried safely
What a tool should remember when a request succeeds but its response disappears. A runnable SQLite example covers duplicate delivery, conflicting intent, and concurrent retries.
8 min read
Invoice disputes need a verified ledger
An invoice-dispute workbench that connects evidence, exact human approval and verified credits, including recovery when a response is lost.
4 min read
A voice assistant has more than one latency problem
Separate turn detection, response generation, playback, and interruption time before trying to make a voice assistant faster. Includes a runnable trace analyzer.
8 min read
A supplier promise is not a recovery plan
A changed delivery date leaves a buyer with stock, cost and approval decisions. This experiment turns supplier terms into a traceable recovery plan.
5 min read
Before building an agent, map the workflow
A practical way to find where an agent belongs in a business process, using a workflow map, explicit decision boundaries, and a runnable support example.
10 min read
Vulnerability remediation needs deployment evidence
A merged patch does not tell a security team what is running. This experiment follows a vulnerability through deployment evidence, human review and rollback.
4 min read
Graph Engineering Is Not a New Discipline. That Is the Point.
A new label is going around for building agentic systems as explicit execution graphs. The label is barely real. The shift underneath it is, and the evidence for and against it is more interesting than either side admits.
12 min read