End-to-end evidence · Runs 1–5 · August 2026

Five experiments. One question: what should the agent execution boundary do?

Why these experiments exist

The problem is not giving an agent an API. It is giving the agent useful capabilities without making the API the execution model.

A conventional endpoint can solve one operation very well, but as agent-facing capabilities multiply, the application can accumulate bespoke tools, repeated orchestration, duplicated policy checks and increasingly large interaction traces. These experiments ask whether a semantic execution boundary can reduce that agent-side work while preserving correctness and application control.

Agent-facing surfaceCan one capability express the business operation without exposing implementation-shaped steps?
Execution boundaryCan authorization, validation and planning remain application-owned rather than becoming model-owned orchestration?
EfficiencyDoes reducing unnecessary interaction also reduce context load and improve execution throughput?
Read the runs as a progression: establish the baseline, scale it, measure efficiency, compare execution architectures, then test a high-assurance business capability.

Foundgine is intended to let an agent express a capability while the application remains responsible for semantics, authorization and execution. These runs progressively test that idea — from a small customer workflow to a high-assurance financial mutation.

Read the current finding ↓
The complete verification story

From isolated contracts to a stateful agent-facing system

The benchmark suite is only meaningful when the execution boundary is verified underneath it. Foundgine's story progresses from deterministic unit behavior, through real PostgreSQL execution and security attack paths, into performance, and finally into the Supply Chain application workflow.

01 · Unit testsSemantic, planning, authorization, MCP, AOT, InMemory and other deterministic contracts.
02 · PostgreSQL integrationReal provider execution against PostgreSQL, including end-to-end state and transaction behavior.
03 · PenetrationAuthorization attacks plus adversarial semantic-input and hostile-model replay coverage.
04 · PerformanceA real Docker performance smoke gate plus larger reproducible CoffeeBeanery benchmark matrices.
05 · Supply Chain E2EAn agent-like workload crossing MCP, semantic execution, authorization, ExecutionIR and PostgreSQL.
Release principleThe CI release path requires the core verification gates before package publication; the Supply Chain E2E adds the application-level proof story.
See the complete Supply Chain story →
01 · Start with agent workHow many tool interactions and how much context does the agent need to complete the same business process?
02–03 · Stress the workflowDoes the reduction survive more customers, more concurrency and a larger amount of orchestration?
04–05 · Change the boundaryDoes the execution architecture matter for graph queries and for a high-assurance business capability?
Supply Chain E2E · New vertical

Agent → MCP → Foundgine → PostgreSQL

The application-level culmination: a stateful agent workload that brings semantic execution, authorization, high-assurance mutations, replay protection and PostgreSQL state integrity together.

Open Supply Chain E2E →
10 entities · 10 relationshipsCustomer, orders, products, inventory, suppliers, warehouses, shipments and carriers.
Mixed workloadValid, invalid and unauthorized agent operations across customer, service, warehouse, procurement and admin identities.
Stateful evidencePlaceOrder covers authorization, ownership, validation, pricing, atomic mutation, idempotency and execution evidence.
Benchmark evidence

Inspect the exact workload and concurrency result

The matrix shows the completed benchmark result for each workload/concurrency cell. Select a cell to compare the conventional and Foundgine execution paths using the published measurements.

Interactive matrix

Run 4 · 4 × 4 execution matrix

Select one workload/concurrency cell to inspect the conventional and Foundgine measurements for that exact experiment.

ConventionalFoundgine
Workload \ ConcurrencyC8C16C32C64

No matrix cell selected yet.

What this cell means

Click a matrix cell above to inspect the benchmark result for one exact workload/concurrency combination.

How to read this together

The matrix tells you what the system did. The published benchmark measurements show how the two execution paths compare.

1 · Select the experiment

Start with a cell such as 10,000 customers · C64. That fixes the exact workload and concurrency being discussed. The result above is the published benchmark measurement for that experiment.

2 · Read the execution result

Compare tool calls, estimated context, latency, throughput and success rate. These describe the agent and application execution path. A lower context figure means less estimated replay context; it does not by itself prove lower electricity use.

3 · Inspect the exact measurements

Use the selected-cell comparison and detailed table to see RPS, wall time, estimated context load and tool calls for both execution paths. The values come from the published benchmark artifacts.

4 · Keep the claims separate

This is deliberate. We can say 87.4% lower estimated context when the benchmark supports it. We should only claim lower energy or carbon when the corresponding energy/emissions measurements were actually captured.

How to read the evidence

Measured and estimated values are labelled separately

Measured benchmark signals include tool calls, request timing, RPS and success/failure counts. The replay harness also computes an estimated context load using the benchmark's documented heuristic; that is not provider billing data.

Estimated context tokens are included because they describe the amount of agent-facing context carried through the workflow. They should not be presented as exact model-provider usage unless the benchmark is run against a live model with provider usage reporting.