AMF Agent — V0.8.0 RC8A

Mission-specific AI, qualified for deployment.
L'IA vient à vos données, pas l'inverse.

AI Mission Foundry (AMF) is an Adaptive Model Foundry for building, qualifying, selecting, and deploying mission-specific AI systems.

AMF Agent is its first public proof product. It is not a fine-tuned Qwen checkpoint, not an adapter, and not a wrapper around a single model. AMF decomposes a mission into capabilities, authorizes execution, evaluates candidate realizations, rejects candidates that fail hard constraints, and executes only the qualified intelligence required for each operation.

No Capability Authorization ⇒ No Execution.

At a glance

Result	AMF Agent RC8A
Publication decision	PUBLICATION_READY
Fresh Final qualified output	100.00%
Fresh Final tool safety	100.00%
Cost / qualified outcome vs best parent	73.55% lower
Qualified throughput vs best parent	278.08% higher
Sequential p95 vs best parent	45.54% lower
Paired interleaved latency	AMF faster on 96 / 96 rows
Authority execution	Strict offline

Work with AMF

Need a qualified, private, deployable AI system for your organization?

AMF turns a mission — plus its quality, safety, latency, cost, memory, privacy, and deployment constraints — into a qualified AI system designed for the target environment.

Stack Modern
Email: contact@stack-moderne.fr
Contact: Faysal BENAHMED

Physical result

Fresh Final V8, 96 rows, NVIDIA A100-SXM4-80GB, same-harness comparison against the best final parent.

Metric	AMF Agent RC8A	Best parent: Qwen3-4B-Instruct-2507
Qualified output	100.00%	77.08%
Critical OK	100.00%	82.29%
Tool safety	100.00%	91.67%
No unauthorized action	100.00%	94.79%
Model calls / request	0.7396	1.0000
Cost / qualified outcome (GPU-s)	0.8459	3.1981
Qualified throughput / GPU-s	1.1822	0.3127
Sequential p95	1.9974 s	3.6676 s
Resident memory	8.0536 GB	8.0539 GB

Measured deltas:

73.55% lower cost per qualified outcome
278.08% higher qualified throughput
26.04% fewer model calls per request
45.54% lower sequential p95 latency

Independent interleaved latency authority:

AMF p95: 2.0912 s
parent p95: 3.6821 s
AMF faster on 96 / 96 paired requests
parent faster or equal on 0 / 96 paired requests

These claims are bounded to the included AMF Agent mission contract, protocol, Fresh Final V8 authority, runtime, and hardware evidence. They are not a claim of universal superiority over Qwen or other models outside this evaluated scope.

Substrate competition

AMF did not select Qwen by preference, branding, or static configuration. It emerged as the physical winner of the qualification process.

Three pinned model substrates were physically evaluated under the same capability-qualification harness:

Substrate	`TOOL_EXECUTION_ARGUMENTS`	`DIRECT_RESPONSE`	Outcome
Microsoft Phi-4-mini-instruct	Not qualified	Not qualified	Rejected
Qwen3-4B-Instruct-2507	Qualified	Qualified	Selected
Mistral-7B-Instruct-v0.3	Not qualified	Not qualified	Rejected

Exact pinned revisions:

Phi-4-mini-instruct: cfbefacb99257ffa30c83adab238a50856ac3083
Qwen3-4B-Instruct-2507: cdbee75f17c01a7cc42f958dc650907174af0554
Mistral-7B-Instruct-v0.3: c170c708c41dac9275d15a8fff4eca08d52bab71

“Not qualified” does not mean that a model is generally bad. It means that the tested realization did not satisfy the frozen AMF qualification requirements for that specific capability, mission, interface, and harness.

Qwen3-4B was the only RAW substrate that qualified both required neural capabilities.

What won

CR0_ATOMIC_CAPABILITY_PHYSICAL_WINNERS

TOOL_EXECUTION_ARGUMENTS
  -> Qwen/Qwen3-4B-Instruct-2507 RAW
  -> AGENT_EXECUTOR_ARGS_V1

DIRECT_RESPONSE
  -> Qwen/Qwen3-4B-Instruct-2507 RAW
  -> AGENT_DIRECT_RESPONSE_CONTENT_V1

Exact Qwen revision:

cdbee75f17c01a7cc42f958dc650907174af0554

The neural model does not generate deterministic Agent fields that AMF already knows. The model is asked only for the atomic, irreducibly uncertain payload; AMF constructs deterministic control and envelope fields itself.

Hard gates first

AMF also evaluated a merged Qwen + LoRA direct-response challenger. It remained semantically qualified, but its deployment footprint violated the frozen memory guardrail.

Candidate	Resident bytes	Memory regression	Pre-Final deployment gate
CR0 RAW/RAW	8,056,627,200	~0%	PASS
Merged direct-response	16,102,238,208	+99.86%	FAIL

Frozen guardrail: maximum +35% resident-memory regression.

The merged candidate was rejected before Fresh Final.

Hard gates first. Optimization second.

This is a core AMF property: a candidate does not become deployable merely because it is accurate or fast. Known deployment constraints are authority gates, not post-hoc observations.

Adaptive Model Foundry

AMF is adaptive at the system-construction level.

Mission
  ↓
Capability decomposition
  ↓
Candidate neural / deterministic realizations
  ↓
Capability qualification
  ↓
Hard deployment gates
  ↓
Physical selection
  ↓
SYSTEM_FROZEN
  ↓
Fresh Final authority
  ↓
Independent verification
  ↓
Qualified deployable system

The model is a substrate. The capability is the unit of qualification.

Routing selects capabilities. Qualification selects realizations. Runtime executes only the cheapest qualified intelligence needed.

Atomic neural execution

AMF follows a simple principle:

Models generate only the irreducibly uncertain payload. AMF deterministically constructs everything already known.

For AMF Agent RC8A, that means:

Request
   ↓
Deterministic policy / authorization
   ↓
Capability router
   ├── deterministic refusal / early exit
   ├── TOOL_EXECUTION_ARGUMENTS → atomic neural payload
   └── DIRECT_RESPONSE          → atomic neural payload
   ↓
Deterministic Agent envelope
   ↓
Qualified outcome

This reduces unnecessary neural work instead of asking a general-purpose model to regenerate known structure on every request.

Offline authority

RC8A stages exact pinned model snapshots before authority. During the physical campaign:

authority_network = FORBIDDEN
model_source_mode = OFFLINE_PINNED_SNAPSHOT

No OpenAI, Anthropic, Gemini, or external inference API is required by the qualified runtime.

This makes private/on-premise deployment possible when the target infrastructure, security controls, licensing, and operational requirements allow it.

Private/offline deployment is an architectural capability, not an automatic legal or regulatory compliance claim.

Publication authority

decision             = PUBLICATION_READY
mission_qualified    = true
system_qualified     = true
efficiency           = true
public_value         = true
publication_ready    = true
independent_verify   = PASS
artifact_integrity   = PASS

AMF artifact SHA256:

2af41068f1e1540dbee39d12ab6f6d18e9b75386698d9ca9c9b5d2c5eb7ea513

Fresh Final V8 SHA256:

ddb426048606fef2dd607a5d0f73e37e990c91af685305faa756dec8f5b50f4d

Physical evidence archive SHA256:

fc9926392759084ea6600f30009c86508ad37d64b66fe676ffaedeca425528b4

Artifact boundary

This repository publishes the qualified system specification and physical evidence.

It does not redistribute Qwen base weights and does not claim that AMF trained the winning Qwen weights.

mode                  = PINNED_RECONSTRUCTION
base_weights_embedded = false
adapters_embedded     = false

The winning neural substrate remains Qwen/Qwen3-4B-Instruct-2507 at the exact pinned revision above.

AMF Agent is therefore a qualified system release, not a newly trained standalone AMF neural checkpoint.

Evidence

system/ — exact publication-ready system specification and identity receipts
evidence/selected/ — Final qualification, independent verification, champion selection, runtime, and deployment receipts
evidence/raw/ — complete exported RC8A physical evidence archive and SHA256
release/RELEASE_SUMMARY.json — compact public release summary

See:

Why AMF exists

AMF is designed for a different question than:

“Which model should we call?”

Its question is:

“Given this mission and these constraints, what is the smallest qualified intelligence that deserves to execute?”

That makes AMF suitable for building expert, qualified, lightweight, deployable AI systems rather than treating a general-purpose model as the entire application.

AMF thesis

Models are substrates. Capabilities are qualified components.

Models generate only the irreducibly uncertain payload. AMF deterministically constructs everything already known.

Hard gates first. Optimization second.

No Capability Authorization ⇒ No Execution.

Build a qualified AI system for your mission

Stack Modern
Email: contact@stack-moderne.fr
Contact: Faysal BENAHMED

AI Mission Foundry — AMF
An Adaptive Model Foundry for mission-specific AI systems.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support