Verified answers
over operational
APIs.
Prodis is an open-source runtime that turns your Django, FastAPI, or Spring APIs into assistants that plan, execute, and validate answers in code before responding. Managed evals, answer review, deployments, and enterprise controls are available when teams are ready to ship.
Premise.
The demo passes. Production is where it breaks.
Every production AI eventually fails the same way. A confidently wrong answer reaches a user¹. An action runs that should have been blocked². A decision is made from a black-box answer the team cannot explain after the fact³. When evidence is missing, Prodis refuses with a recorded reason⁴. Polished language is not correctness, and the model is not the authority for that distinction.
Method.
The model proposes. The backend executes.
Break question-answering into granular, schema-validated steps, and a non-deterministic task becomes an almost-deterministic one. The model interprets language at the seams; bounded, typed code owns the rest. The answer record shows the explicit inputs from the user, derived inputs from resolvers, implicit inputs from runtime context, and each step used to reach the final answer. Synthesis happens only after evidence is sufficient — and the system can refuse.
Stack.
Today's agent stacks run the loop. They do not own correctness.
OpenAI SDK, Anthropic SDK, LangChain, LangGraph, MCP, direct tool calls, in-house loops — useful tools, incomplete control boundary. They call models, route tools, stream responses, and wire workflows. They do not make the backend the authority for answer eligibility over business APIs. In the usual loop, the model still decides whether the evidence is enough. Prodis moves that boundary into code.
- 01user asks
- 02model picks tools
- 03api returns data
- 04model decides if enough
- 05model writes answer
- 01model interprets intent
- 02plan compiled + validated
- 03authorized APIs execute
- 04result derived in code
- 05answer readiness checked
Prodis owns the correctness boundary, not just the final check. Intent, plan, permissions, evidence, derivation, readiness, synthesis: each step has a backend-owned contract.
Runtime.
Open-source runtime. Framework adapters are the on-ramp.
Prodis ships the engine, contracts, local runtime, adapters, eval runner, and examples as open source. Install the adapter in a Django, FastAPI, or Spring service; it introspects what's already there and produces typed endpoint contracts the runtime validates plans against. Your APIs stay where they are. No parallel inventory, no rebuild around an AI framework.
A full pilot integration in 2-3 days.
Correctness controls from day one.
Connect a real API surface, keep the model-calling code you already have, and ship an assistant with answer records without restructuring your service.
Apparatus.
What makes the answer verifiable.
The control surface missing from the existing stack. Each capability is owned by code, not by prompts; each leaves an answer record the team can explain after the fact.
-
01
Typed endpoint contracts
Capture request and response semantics in machine-usable contracts the runtime validates plans against.
-
02
Validated planning
Reject invalid or unsupported plans before execution instead of repairing bad tool calls after the fact.
-
03
Evidence sufficiency
Make answer readiness explicit so the system knows when evidence is complete and when it is not.
-
04
Deterministic derivation
Use controlled computation for totals, comparisons, rankings, and grouping over API data instead of prompt-side math or guesswork.
-
05
Answer provenance and explainability
Inspect the inputs and execution steps behind each answer, so the final output is explainable rather than a black box.
Field.
Already piloted in three industries. Internal workflows and customer-facing commerce. Same hard requirement: the answer has to be right.
These pilots were chosen because correctness is not cosmetic. Operators and customers act on the answer; when evidence is missing, the system must say so. FMCG retail, market research, and fintech share little operationally. They hit the same boundary: useful AI is not enough without backend-owned evidence, permissions, and refusal.
RSVP.
Early preview by request.
Engineering teams shipping AI over operational APIs, with backend ownership of correctness. Join the private waitlist for early product updates, open-source launch access, and managed pilot availability.
RSVP → waitlist@prodis.ai