Execution Systems·2025·Built
    Execution Engine

    UniConvert

    Local-first execution engine for AI-assisted pipelines

    PythonRustSQLiteTemporal (optional)Docker
    99.2%
    Execution success rate (prototype)
    <5 ms
    Plan validation time
    100%
    Replay fidelity (20 test runs)
    8
    Built-in policy checks

    UniConvert is an execution engine for AI-assisted work: plans are data, steps declare inputs/outputs, and each transition passes through validators (schema, policy, capability). It integrates with LLM agents where helpful, but never conflates planning with execution authority.

    Design goals:

    • Local-first runs for sensitive transforms; optional remote executors for heavy jobs.
    • Replayable runs: hashed artifacts + step logs for debugging and compliance.
    • Composable pipelines as graphs with explicit failure domains and compensating actions.
    The challenge

    Agent demos chain tools cheerfully; production needs idempotent steps, typed IO, and blast-radius control. Silent partial failures and non-deterministic side effects are unacceptable when AI proposes plans.

    The challenge is to make agentic workflows boringly reliable: validate first, execute once, record everything.

    Approach
    1. Plan IR: Represent tasks as a DAG with explicit contracts (pre/post conditions).

    2. Validators: Static checks (schema, dependency order) + dynamic checks (secrets, network policy).

    3. Executors: Sandboxed local processes or signed remote workers; uniform telemetry.

    4. Compensation: Declared rollback hooks for reversible steps; explicit manual escalation when not reversible.

    System architecture
    Planner (LLM)
    Plan IR
    Validators
    Executors
    Artifact store
    Input
    Process
    Model
    Storage
    Output
    Failure modes
    • 01

      Third-party APIs fail mid-DAG—handled with retries, idempotency keys, and partial replay.

    • 02

      Validator false positives block legitimate plans—versioned allowlists and override workflows.

    • 03

      Large artifacts blow storage budgets—compression tiers and external blob offload.

    Trade-offs
    • 01

      More ceremony than a script; necessary for production-grade agents.

    • 02

      Local-first prioritizes privacy/latency over elastic scale—remote executors optional.

    • 03

      Strict validation can slow iteration—mitigated with dev-mode profiles.

    Implementation details

    run_plan.py

    Execute only after all validators pass

    python
    run_plan.py
    🐍python
    1 
    Ownership

    Designed

    Defined plan IR, validation stages, and executor contracts for local vs remote work.

    Implemented

    Implemented the runner core, artifact hashing, and policy hooks.

    Scrapped

    Implicit tool calls directly from model output—replaced with explicit compile + approve flow.