Skip to content
IKANGAISignals
Sign in Request a walkthrough

The financial close for project businesses

Between month-ends,
your portfolio still moves.

Signals runs the money side of delivery — cost sheet to purchase order to invoice to timesheet to a governed monthly close — and keeps watching between closes. Margin erosion, cost overrun, schedule slip and cash risk are detected by domain math, ranked, and handed to the person who can still do something about them.

  • The month actually closes — locked, approved, attested
  • Detection is arithmetic, not opinion
  • The model is optional and swappable
  • Self-hosted — you own the database
Signal feed example data
critical margin_erosion project

Nordwind Rollout — margin down 4.2 pts against baseline

metric
gross_margin_pct
value
21.8%
threshold
26.0%
Δ
−4.2 pts

Open project · costs

warning cash_risk customer

Halvorsen AS — €184,300 aged past 60 days

metric
ar_61_90
value
€184,300
threshold
€150,000
dso
74 d

Open receivables · aging

info schedule_slip project

Terminal Upgrade — SPI below 0.90 for two closures running

metric
spi
value
0.86
threshold
0.90
periods
2026-06, 2026-07

Open project · earned value

01 — the gap

Attention is periodic.
Exposure isn't.

A portfolio review is a snapshot. Between two of them a burn rate doubles, a milestone quietly slides, an invoice ages into the 90-day bucket, a resource ends up committed at 140%. All of it is already in the system — in the closure, the timesheet, the supplier invoice, the allocation matrix.

Nobody is short of data. What is missing is something that reads it on every tick, decides what actually became material, and says so while it is still cheap to fix.

The month-end number is a verdict.
A signal is a warning.

Periodic attention versus continuously accumulating exposure Management attention spikes at each month-end and decays between; exposure rises continuously across the same period.
Management attention Accumulated exposure

02 — architecture

Harness ⊗ Loop ⊗ Model

An intelligent system is three parts, and capability is dominated by the first two. Most products in this space are a model with a thin wrapper. Signals is the other way round: the hard, durable part — a full portfolio management system with the domain math already in it — is the part that was built first.

01

Harness

The running system. World state and domain expertise.

A live database of projects, cost sheets, earned value, closures, capacity, invoices and acceptance — plus the deterministic detectors that compute over them. PMO practice encoded as arithmetic rather than as prompts.

Durable · model-agnostic · already built

02

Loop

The iteration that turns state into intelligence over time.

Sense, detect, reconcile, explain, rank, recommend, record, observe the outcome, adapt. Continuous rather than requested. This is what makes the system notice things instead of answering questions.

The compounding part

03

Model

A reasoner plugged into one step. Interchangeable.

The model writes the explanation and helps with priority. It never manufactures evidence. Swap it, downgrade it, or configure none at all — the deterministic signals still fire, with templated explanations in your language.

Commodity · swappable · optional

Which is also the risk answer: nothing here is a bet on one vendor's model, and none of your portfolio data has to leave your infrastructure to make it work.

03 — the loop

One tick, nine steps

The sweep runs on a schedule against the same service layer the application uses. It is convergent: re-running it never duplicates a signal, and a condition that has cleared resolves itself on the next pass.

  1. 1SenseOne consistent read of the estate
  2. 2DetectPure domain math per source
  3. 3ReconcileUpsert, dedupe, auto-resolve
  4. 4ReasonModel reads the evidence
  5. 5RankSeverity × recency × priority
  6. 6ExplainWhy it fired, in your locale
  7. 7RecommendA deep link into the write surface
  8. 8RecordLedger of every state change
  9. 9ObserveActed on, or dismissed — and learn

Humans stay in the loop

Signals recommend; people decide. The loop holds read scope only — it never edits a project, a closure or an invoice. Every recommendation is a link into the one surface that owns that change.

Noise discipline

A candidate has to clear a configured materiality threshold before it is ever raised. The model may demote a signal; it cannot promote one into existence. Cleared conditions expire themselves.

No cold start

Detection is threshold and earned-value arithmetic on your live data — not a model trained on someone else's portfolio. It is useful on day one and explainable on day one.

04 — evidence

Every signal shows
its arithmetic

The line between what is computed and what is written is drawn in the data model, not in the marketing. Evidence is deterministic and reproducible: same inputs, same numbers, no model involved. Only the prose varies with the reasoner.

deterministic
Metric, value, threshold, delta, period, detector key, ruleset version.
model
The explanation, the drafted recommendation, the ordering hint — validated against an allow-list before it is stored.
provenance
Which detector, which ruleset, which model, which build — recorded on the row, so any number can be justified months later.
signal · 8f21c4 anatomy
signal_type cost_overrun
severity critical
evidence { metric: "cpi", value: 0.81, threshold: 0.90,
  delta: −0.09, period: "2026-07" }
explanation Cost performance fell below the critical tier for the first time this year. Actual cost is running 23% ahead of earned value, driven by manpower in the last two closures.
recommended Review the cost breakdown before the 2026-08 lock
detector evaluateIndexBreaches · ruleset v3
model configured per instance · nullable

Remove the model and rows 4–5 fall back to a templated explanation. Rows 1–3 and 6–7 do not change.

05 — coverage

What it watches

Nine signal families, each wrapping a detector that already runs against your portfolio. Thresholds and severity tiers are configuration, per instance — not constants baked into a vendor's idea of a healthy project.

06 — the book of record

A signal is only as good
as the ledger behind it

Detection needs a plan to compare against, actuals to compare with, and a governed month-end that decides which numbers are final. Tracking budget against actuals continuously is table stakes — producing a frozen, approved record of each month, reconciled, drift-disclosed, and hashed into a chain, is not. That close is the product, and it runs a delivery organisation on its own.

Both sides of cash

  • Cost sheets & versions
  • Multi-currency at quoted rates
  • Customer POs → invoices → collection
  • Supplier POs & supplier invoices
  • AR ageing & collections queue
  • Change requests

Delivery

  • Projects & baselines
  • Milestones, deliverables & schedule
  • Acceptance & quality KPIs
  • Work items & tracker sync
  • Capacity & allocation
  • Risks & issues

The close

  • Earned value per month
  • Monthly close: snapshot, reconcile, lock, approve
  • Drift disclosure on archived figures
  • Attested archive — hashed & chained
  • Timesheets, approvals & delegation
  • Audit trail
12snapshot tables frozen per project, per month, at close
2sides of cash — receivables and payables in one model
SHA-256content hash at approval, chaining each month to the last
0per-seat licences — self-hosted on your own infrastructure

agent-native

The same surface, for people and for agents

Everything the interface can do is also reachable over a command-line client and a Model Context Protocol server, under a real user's token and the same permission model. Point your own assistant at the portfolio: it gets exactly the access that person has, and every write lands in the audit trail with a name on it.

  • MCPRemote server with OAuth 2.1, tool discovery, redacted scope for PII-free reads
  • CLI~250 commands, JSON in and out, dry-run on every write
  • RESTThe API the application itself runs on — no second-class integration path

07 — who it is for

Built around the month-end,
not around a dashboard

PMO

Portfolio-wide exposure, a closure pipeline that chases itself, approvals with an audit trail — and a month-end record Finance can stand behind.

Project managers

One project cockpit: plan versus actual, what is blocking the close, what needs deciding this week — scoped to the projects you own, and nothing else.

Delivery teams

Timesheets, leave, and the work assigned to you. Small surface, few clicks, no access to anyone else's numbers.

Next

See it against
your own portfolio

A walkthrough runs on a demo estate first, then on a copy of yours. Self-hosted on your infrastructure, or run by us — the data model and the detectors are identical either way.