Inferventis
Systems Architecture · Living Document · April 2026
End-to-end system schema
How a client agent intent becomes a tool call — and how we make our tools win. Read left → right.
Client agent
Client Agent
An autonomous AI agent running locally or in the cloud. Receives a user task and determines an external tool is needed.
· Name & description
· System prompt — behaviour & persona
· LLM — Claude / GPT / Gemini / other
· Tool list — MCP server connected
· Memory — context window + history
· Trigger — user / schedule / event
· Output — user / agent / system
Any MCP client
semantic
broadcast
(embedding)
Network layer
Edge nodes
Cloudflare Workers deployed globally. Intercepts manifest requests before they reach origin. Returns cached responses in under 20ms from the node nearest to the calling agent.
Planned
Semantic path cache
Recognises semantically equivalent intents across different agents. "Current weather in London" and "Temperature in London right now" resolve to the same cached skill path — no re-embedding required.
Planned
Regional replicas
Manifest index replicated across global regions — Europe, North America, APAC, Middle East. Broadcast hits the nearest Inferventis node first, returning results before unoptimised registries can respond.
Planned
Micropayment layer
x402 protocol live on /mcp-pay. HTTP 402 challenge issued per tool call → agent pays USDC on Base → Coinbase facilitator verifies on-chain → tool served. Stripe MPP implemented (pending merchant token). Base Sepolia testnet live and verified. Mainnet: swap two env vars.
Live — testnet
optimised
manifests
written
Optimisation engine — core IP
Manifest quality scoring
Every manifest scored on field completeness, description richness, example coverage, and precondition clarity. Quality bonus (20% weight) applied per call. Richer manifests win by design.
Live
Telemetry capture
Every tool call logs: calling model, tool selected, intent query, latency, success/fail. Accumulates as proprietary dataset per LLM × tool pair. The raw material for all optimisation.
Live
A/B variant testing
Multiple description variants run simultaneously per tool. Selection rate measured per variant per calling model. Winning variant promoted. Challenger variants continuously introduced.
In development
Judge LLM eval loop
Synthetic eval pipeline. Judge LLM tests variants against thousands of generated intents. Measures trigger rate and hallucination rate per tool × model pair. Runs on every model version update.
Planned
Per-model manifest variants
For each tool × LLM pair a separately tuned manifest is maintained. Claude: precise bounded descriptions. GPT-4: action-first natural language. Gemini: schema-focused. Mistral: concise enterprise. 16 variant files live across 4 tools × 4 models.
Live
Dynamic manifest serving
Calling model detected from model_hint in request. Correct per-model variant served automatically. Falls back to base manifest if no variant exists. variant_id returned in results for tracking.
Live
MCR — Multi-model Contextual Registry
Live FX via open.er-api.com. No auth. ISO 4217. Rate + converted amount + timestamp.
Optimised · standard
Stripe test mode. Payments, charges, customers, subscriptions. Real data.
Optimised · premium
TrueLayer. 300+ UK/EU banks. PSD2. Sandbox blocked — realistic mock data active.
Optimised · premium
Real-time stock prices. Company info, sector, intraday high/low, % change.
Optimised · standard
fx_converter
currency_basic
Demo foils — identical handlers, weak manifests. Prove optimisation delta.
Unoptimised
payment_tool
bank_data
stock_tool
Demo foils — identical handlers, weak manifests. Prove optimisation delta.
Unoptimised
Connectors
open.er-api.com
Free FX rates. No auth required. 60+ currencies.
Live
Stripe API
Test mode. sk_test key in Secret Manager.
Live
Finnhub
Free tier. Real-time stock quotes. API key in Secret Manager.
Live
TrueLayer
Open Banking. 300+ UK/EU banks. Sandbox incident March 2026.
Blocked
Companies House
UK company registry. Free API. No auth required.
Planned
Platform services
Auth
x-api-key header. Secret Manager. SHA256 log hashing. 401 on failure.
Live
Stripe billing
Metered. api_transaction + agent_task meters. €0.05/unit. Non-blocking.
Live
x402 / MPP payments
Per-tool payment mode via env vars (none/x402/mpp). USDC on Base Sepolia testnet verified 2026-04-28. Coinbase facilitator. Stripe MPP ready — pending merchant token. All tools default to none.
Live — testnet
Telemetry
Cloud Logging. Two event types: (1) call events — tool, latency, success. (2) optimisation events — intent, model_hint, variant_served, variant_id, full_ranking, runner_up, margin, is_optimised_winner. Intent corpus feeds A/B loop.
Live
CI/CD
Cloud Build on push to main. Artifact Registry → Cloud Run auto-deploy.
Live
Stripe Connect
Automatic developer revenue splits. 80/20 early, 70/30 standard tier.
Planned
Output
Client Agent
Receives structured tool result. Continues reasoning. Delivers answer to user or downstream system.
Task complete
Data layer — three stores, one flywheel
Hot events — Cloud Logging
Every tool_finder call emits a structured optimisation_event.
Fields: intent · model_hint · variant_served · variant_id · tool_selected · discovery_score · runner_up · margin · full_ranking · is_optimised_winner
The intent field is the critical data point — it tells us exactly what agents asked for when they selected or bypassed a tool.
Live
Intent corpus — Cloud Storage
Daily JSONL files: intents_YYYY_MM_DD.jsonl
Each line: timestamp, session_id, model, intent (raw text), embedding (384-dim vector), tool_selected, variant_served, discovery_score.
Feeds Judge LLM eval loop. Enables semantic clustering — "78% of FX intents contain invoice language."
Planned
Variant ledger — Firestore
Per variant per model: calls_served, times_selected_rank_1, selection_rate, avg_discovery_score, avg_margin, status (active/challenger/retired).
Drives A/B winner promotion. Maps to Stripe Connect — higher selection rate = higher developer revenue bonus.
Planned
Optimisation engine — the core IP (runs continuously beneath every call)
Intent received
→
Model detected
→
Variant selected
→
Vector embedded
→
Similarity scored
→
Quality bonus applied
→
Tool selected
→
Optimisation event logged
→
Intent + variant stored
→
A/B data accumulated
→
Variant ledger updated
→
Winner promoted
→
Score improves
↩ repeat
Commercial flow
Stripe metered — human operators / developers
Agent operator
pays £0.02/call
→
Inferventis margin
£0.01 (100%)
→
Developer receives
£0.01/call
→
Developer earns
10× vs self-hosted
→
Cloud licence
Huawei / AWS / Azure
→
Inferventis takes
30% of their margin
x402 micropayments — autonomous agents (live testnet · mainnet ready)
Autonomous agent
pays $0.001 USDC
→
x402 on Base
settles in ~2s
→
CDP wallet receives
USDC on-chain
→
Coinbase converts
USDC → GBP
→
Revolut Business
fiat treasury
→
Spend via card
or bank transfer