the model · deep dive

The model that holds
your whole system.

A typed, provenance-verified graph of how your system actually runs. Code through runtime. Identities resolved, edges explicit, every edge carrying a confidence and a source.

◢ system.model / live
last verified 0s ago
11 nodes · 10 edges · conf ≥ 0.4
verifying
§01 · anatomy

What the model is made of.

Six properties. Six rules. Every claim the system makes is one of these six. Nothing more.

01node

Every repo, package, endpoint, queue topic, database, dashboard, deploy, or runtime container. Each carries a stable identity that survives renames.

repo:acme/payments · pkg:@acme/payments-client
02edge

Every relationship between nodes: imports, calls, declares, consumes, deploys, runs, owns. Each carries a confidence in [0,1] and a source.

consumes-endpoint · 0.94 · openapi + observed-rpc
03confidence

A confidence per edge from one or more extractors, merged via noisy-OR. Walks across the graph multiply, so distance pays a cost.

0.94 verified · 0.61 inferred · no value → unknown
04provenance

Every edge cites the extractor and the location it came from. You can trace any claim back to a line of code, a span, a manifest.

src=openapi spec=acme/payments/openapi.yaml#L412
05freshness

Every edge carries a last-verified timestamp. The model knows when its own facts went stale. Old answers do not get to pretend to be current.

last_verified = 2026-06-30T04:11:02Z · ttl = 24h
06runtime overlay

Observed reality from traces, eBPF, the bus, the cluster. Confirms, downgrades, or contradicts the declared graph beneath it.

declared:0.91 observed:0.97 merged:0.94 confirmed
§02 · foundation

The code graph. The OSS wedge.

One command, anywhere. Extractors walk the source: imports, declared endpoints, gRPC and protobuf, OpenAPI, wrapped clients, queue topics, env-coupled databases. The edges no formal-schema tool can see.

◢ blast.radius / live
payments / a8f3c21 → main
◤ HIGH·6 nodes potentially affected·comment posted
radius = 3 / nodes = 6 / conf ≥ 0.2
watching for edits
blastmap-botbotcommented on this pull request
2 minutes ago

Radius HIGH · 7 node(s) potentially affected

This PR changes acme/payments (a8f3c21) across 4 file(s). Walking the graph from this repo, 7 downstream node(s) are reachable within 3 hop(s) at confidence ≥ 0.2.

nodetypedistanceconfidencereasoning
repo:github.com/acme/checkoutrepo10.94via consumes-endpoint
pkg:npm:@acme/payments-clientpackage10.91via imports-package
endpoint:POST /v2/chargeendpoint10.88via declares-endpoint
repo:github.com/acme/ordersrepo20.72via consumes-endpoint → consumes-endpoint
repo:github.com/acme/billingrepo20.61via consumes-endpoint → consumes-endpoint
pkg:npm:@acme/event-buspackage20.48via imports-package → imports-package
repo:github.com/acme/audit-logrepo30.32via consumes-endpoint → observed-rpc

How to read this:

  • confidence is the multiplied confidence along the cheapest path from this repo to the listed node. Higher = stronger evidence the edge actually exists.
  • Treat high-confidence rows as places to read carefully; low-confidence rows as places to glance.

Generated by blastmap at 2026-05-23T18:34:02.000Z.

Blast radius is one query over the model. It walks every edge from a changed node and ranks the downstream nodes by the multiplied confidence of the cheapest path. The PR comment is the most boring place that query can live.

§03 · every environment

One model. Four realities. Side by side.

The same edges, the same identities, resolved against every environment you ship to. Drift between prod and staging is named, not hidden. Diffable and routable to the owner.

◢ environments / live
4 environments · 7 services shown
serviceprod-euprod-usstagingdev
billingv412v412v412v411
checkoutv89v89v87v87
authv22v22v22v22
provisioningv110v108v110v110
searchv77v77v77v75
notificationsv41v41v41v41
reportingv18v18v17v17
drift between environments, named not hidden
5 drifts detected · routed to @platform
§04 · observe

Wire runtime in. The graph becomes a twin.

The static graph tells you what was supposed to be true. The runtime overlay tells you what is true right now. Edges get confirmed, downgraded, or contradicted against the real system.

◢ fleet.health / live
8 / 142 services shown
api-gateway
18 msok
auth
12 msok
checkout
24 msok
orders
19 msok
payments
22 msok
billing
14 msok
fraud-ml
41 msok
event-bus
9 msok
confirmed via runtime · 4s ago
8 services · 8 ok
◢ changes / live
last 24h · 412 events
deploy
checkout·rolled v412 to prod-eu / 6 pods
@auto
every action the system took, ranked by recency
t=0.0s
k8s · cluster

Pods, services, ingresses, hpa, deploys. What is actually running at what version, where.

traces · ebpf

Observed RPCs, observed DB queries, observed bus consumption. The edges no schema declared.

logs · alerts

What hurt, when, where, with which input. The ground truth that grounds every verdict.

cost · billing

Spend over the graph instead of over a CSV. The module behind every dollar.

bus · queues

Topics, consumer groups, lag. The conversation the system is having with itself.

people · heads

Owners, on-call rotations, recent context. The map that always lived in heads.

§05 · act

Agents fall out of the model.

Once the substrate is verified and live, an agent can run on it without guessing. Five agents derived from the model, each doing one operational job end to end.

§06 · trust floor

Four bets we made.

Non-negotiable. They are the boundary conditions that make anything built on the model safe to trust.

I.

Invisible relationships are the moat.

Most cross-service edges hide inside wrapped HTTP clients, string URLs, dynamic dispatch. blastmap finds them where formal-schema tools physically cannot.

II.

Confidence is a first-class property.

Every edge carries a confidence in [0, 1] from one or more extractors, merged via noisy-OR. Every walk ranks by it. No false certainty, anywhere.

III.

Org context is auto-injected.

Your stack, your conventions, your active migrations, captured once at init and prepended to every LLM call. The model never reasons about your code blind.

IV.

OSS-first, bring your own LLM.

Run it on your laptop or in your VPC. Plug in Anthropic, OpenAI, Google, or local via Ollama. Your code never leaves your network.

§07 · surfaces

The model meets you where you work.

Six surfaces, one substrate. Run the query from the CLI, read the digest in markdown, ask the question from Claude or Cursor, get the comment on the PR. Same answer, every time.

CLI

bunx blastmap. Init the world, run the queries, ship the digest.

PR comment

Bot posts the confidence-weighted blast radius on every pull request.

MCP server

Claude, Cursor, or any agent gets 12 read-only tools over the model.

Assistant

Plain-English questions over the model. Cited answers, no guessing.

Markdown docs

Browse the live graph as files. Diff it in git.

Webhooks

Subscribe to changes. Trigger your own systems on confirmed edges.

pre-launch · v0.1 incoming

Ship without fear
of the unknown.

Get the v0.1 launch notification and a 30-day head start before public release.

we'll only email you twice. no marketing.