Deterministic AI orchestration — agents that run the same way every time

ForgeShift turns probabilistic agents into repeatable infrastructure for software development. A fat platform holds every workflow, hook, and state for software development — so the agent stays thin, disposable, and governed. Same input, same path, every run.

Hook-enforcedOutcome-optimizedState-managed
workflow.runDeterministic
P1SetupPassed
P2DiscoveryPassed
P3DesignPassed
P4BuildPassed
P5VerifyRunning
P6DeliverQueued
The model

Thin agent. Fat platform. Thin skill.

Determinism comes from where you put the intelligence. Agents are disposable and hold nothing. The platform holds all persistent state, knowledge, and enforcement. Skills are thin routes into a codified library.

Layer 01

Thin Agent

Spawned, scoped, and discarded. Holds no memory and makes no rules — it only executes the workflow it was handed. Disposable by design.

Layer 02 · Core

Fat Platform

The source of truth. State, knowledge, hooks, and codified workflows live here — versioned, enforced, and replayable. The platform is what makes runs deterministic.

Layer 03

Thin Skill

A routing skeleton, not a knowledge base. Skills point to the Tier-2 library where the real domain logic is codified once and reused everywhere.

Core principles

Five rules the platform enforces

Not guidelines. Not best-effort. Every one is wired into hooks, scripts, and gates that run on every tool call.

1

Platform over improvisation

If a protocol, hook, or script exists for the task, it gets used. No reinvention per run.

2

Hooks govern every tool call

Pre- and post-tool hooks are deterministic enforcement layers, not suggestions.

3

Agents are disposable; state is not

All persistent state lives on the platform. Kill an agent at any time — nothing is lost.

4

Context is a budget, not a workspace

Large corpora and multi-file work fan out to background agents, keeping the main context lean.

5

Roles are enforced, not assumed

Orchestrators coordinate; workers implement. Every BRC pair ships a PR plus a review agent.

The workflow

Every task walks the same six phases

Routed at the start, gated in the middle, verified at the end. No phase is skipped, combined, or improvised — the router decides the path, the hooks hold the line.

P1

Setup

Workflow registration, triage, and git validation. The path is decided — and the run recorded — before any work begins.

P2

Discovery

All research runs through background agents on a research protocol. Read-only — structure and blast radius, before a line changes.

P3

Design

Blueprint, architecture documentation and implementation plan with a dependency graph and task queue, approved at a human gate before build.

P4

Build

Built-in debate where every task gets a development and QA worker pair as background agents. Each completed pair ships an incremental PR and a review agent.

P5

Verify

Compliance checks, the full test suite, and coverage verification run before anything is allowed to ship.

P6

Deliver

Incremental PRs merged, Layer 3 multi-select, and the outcome recorded back to the platform for the next run.

What the platform gives you

The machinery behind every deterministic run

Four primitives carry the guarantees. None of them live in the agent — all of them survive it.

Enforcement hooks

PreToolUse and PostToolUse hooks intercept every call, blocking off-policy actions deterministically — the agent cannot route around them.

Persistent state

Sessions, handoffs, and knowledge live on the platform — not in a context window. Resume, replay, or audit any run after the fact.

Background workers

Build–Review–Critique pairs run in isolated background contexts, fan out in parallel, and report back without bloating the orchestrator.

Code-graph nav

A queryable graph answers blast-radius, callers, and importers before edits — so plans are grounded in the real shape of the code.

The lessons, in the platform

Best practices wired into an orchestration system

Every principle above is enforced in our own orchestrator — the deterministic platform. Here's the concrete mechanism that makes each one hold, not hope.

01 · Context rot is the enemy

Curate the context; don't hoard it

Skills and knowledge load only when a task needs them, finished work is compacted into saved state, and heavy jobs run in separate agents — so the working context stays small and focused.

02 · Markdown is a suggestion

Rules that must hold are code, not prose

Anything the system must always do is enforced by a script that runs automatically — not written as a guideline in a document the model is free to skip.

03 · Enforcement outside the model

A gate checks every action before it runs

Before each tool call a deterministic check runs and can physically block a disallowed action. It doesn't ask the model to comply — it removes the option.

04 · Config lives in structured files

Thresholds are exact values, not adjectives

Every gate condition and limit is a concrete number in a config file. A number gets obeyed; a sentence about 'warnings' gets interpreted.

05 · The process, in phases

Every task walks the same fixed stages

Work always flows plan → build → verify → ship, and each stage has an exit gate that must pass before the next begins. Testing is structural, not optional.

06 · Thin agent, fat platform

Disposable workers; the platform holds the memory

Workers are spawned to do one task and thrown away — for a build, a dev worker and a reviewer worker check the same task, then vanish. All durable state and knowledge lives in the platform, not the worker.

Bonus · Runtime secret injection

Secrets that never touch disk

Credentials are pulled from a vault the moment a command runs and passed straight into that process's memory — never written to a file, never committed to the repo, and gone the instant the command exits.

1Fetched from the vault at run time
2Injected into process memory only
3Discarded when the command exits

No .env file. Nothing on disk. Nothing in git.

Stop hoping your agents behave. Make them.

Put the intelligence in the platform, keep the agent thin, and ship runs you can replay, audit, and trust.

Book a discovery call →
Common questions

Questions about deterministic orchestration

Book a discovery call

Tell us what you're trying to make deterministic — we'll walk your setup and where the platform fits.

  • We walk your current agent setup together
  • A concrete next step, not a sales call
  • A reply within one business day
Book a discovery call

Expect a response within one business day.