A HARNESS BY BLACKSQUID ENGINEERING

Figure it out
before you build it.

Your idea deserves more than another AI chat.
Bring the model you already use. Explore the questions and evidence on one connected board.
See what holds up. Leave with a plan you can build.

BRING YOUR OWN INTELLIGENCE · WE PROVIDE ITS ARTICULATION · PAID BY CREDITS

SCROLL TO EXPLOREIDEA × BOARD × PLANUTC --:--:--
SOUND FAMILIAR?WHY THIS EXISTS

Building is easy now.
Knowing what to build is not.

Most ideas fail before the first line of code. Not because they were bad. Because nobody worked them out.

  1. 01

    You open five chats and forget what the third one said.

    Every chat is a straight line. Your thinking is not.

  2. 02

    The AI writes ten pages. You read two.

    The important sentence is in there somewhere.

  3. 03

    You copy things into a doc, then another doc, then lose both.

    Links, notes, screenshots. All over the place.

  4. 04

    The AI talks you into something. You can’t trace back to what you wanted.

    Where did this start? Why did I change my mind?

  5. 05

    At the end you have a hundred pieces and no plan.

    So you start building anyway. And find out the hard way.

FIVE CHATS AND A DOCWHERE THINKING GETS LOST
Scattered chats and notes become one connected boardThree chat windows full of text, a notes document with pasted fragments and loose links sit on the left with no connections. An arrow leads to one board on the right where the question, the evidence and the decision are linked, with one open question still visible. CHAT 1 CHAT 2 CHAT 3 10 pages. Read 2.Drifted off.Forgot this one. NOTES.DOCPASTED · PASTED LINK PDF SCREENSHOT ?WHERE DID I START?No way back to the first thought. ONE BOARDNOTHING LOST 01 / THE QUESTIONWhat do I actually want? 02 / THE EVIDENCEWhat holds up, and what didn’t. 03 / THE DECISIONWhy this. With the sources. INFORMSSUPPORTS ?STILL OPENVisible until answered.
Left: how it goes today. Right: the same thinking on one board, connected.
HOW IT WORKSFOLLOW THE THREAD ↓

You don’t need the answer.
Just a place to start.

Bring a messy idea. Work it out on one board.
Leave with one clear plan.

  1. 01 / THE QUESTION“What if…?”A hunch is enough.
  2. 02 / ONE BOARDWork it out.Nothing gets lost.
  3. 03 / ONE CLEAR PLANWrite it down once.Your build tool follows it.
  4. 04 / YOUR NEXT MOVESoftware. Hardware.Take it where you build.
WORKING EXAMPLE / THE TERRACEQUESTION → REVIEW → OPTIONAL PACKAGE
01 / IN YOUR INVESTIGATION

A question you can keep working on.

Why is the café terrace empty when the sun comes out?
On the canvas
A paper and weather observations, with their connections visible.
Still open
Does shade change what people feel at the table?

An illustrative question, not a research result.

02 / IF YOU CHOOSE TO BUILD

Review the scope first.

Mark the cards, notebook entries and answers that belong. A scope check can point out omissions; you choose what to include.

PACKAGE VIEWER / SCHEMATICAFTER COMPOSITION
A product, defined.
OverviewBuild planFull spec
Overview
Problem, solution idea and open questions
Build plan
Modules, waves, PRDs and checks
Full spec
The complete Markdown definition

What you can take away Once a full package is composed, download an archive with PACKAGE.md, AGENTS.md and one PRD per module. Hardware files depend on the package.

Schematic example of the harness at work. An investigation remains useful on its own; a build package is a separate step you choose.
01 / FOLLOW A QUESTIONHUNCH → EVIDENCE

Pull on a thread.
See what connects.

A paper. A weather feed. Something you noticed. Put them on the same canvas and start asking better questions.

Ask the AI about a selection, send an agent to research, or test a hunch against data. Keep the evidence that holds up. You decide what belongs.

Explore the canvas
OUR EXAMPLE STARTS HERE
“Why is the café terrace empty when the sun comes out?”
THE TERRACE INVESTIGATIONILLUSTRATIVE EXAMPLE
A question becomes a connected investigationA research paper on thermal comfort and hourly weather observations connect to a café question. Together they suggest testing local conditions, with shade still an open question. 01 / RESEARCH PAPERComfort isn’t justair temperature. 02 / WEATHER OBSERVATIONThe sunny hours.09:0018:00 03 / A BETTER QUESTIONWhat does it feel likeat the table? INFORMSTESTS ?WHAT ABOUT SHADE?Keep the uncertainty visible. A DIRECTION TO TESTMeasure the conditions. Show the pattern.
Connect sources. Challenge assumptions. Keep the reasoning.
TRY THE CANVASGet your hands on the canvas.

Move the cards, follow the agent’s thread, or change a temperature assumption in this interactive example.

02 / GIVE THE IDEA A SHAPEEVIDENCE → DEFINITION
YOUR SOURCESYOUR DECISIONSYOUR CONSTRAINTS
BUILD PACKAGE / 001
THE TERRACE PROJECT

A little less guessing.
A better place to sit.

A local comfort monitor for small cafés.

01Who it helps & whyTHE PROBLEM
02What to build & howTHE SYSTEM
03What “done” meansTHE TESTS
EVIDENCE INCLUDED↳ READY FOR YOUR NEXT STEP
Illustrative package · Your investigation supplies the content.

All that thinking.
One clear definition.

Select the evidence worth building on. Create a build package. The harness turns it into a bounded product definition with the context your next tool needs.

  1. 01

    A reason to build.

    The problem, the people and the evidence behind your idea.

  2. 02

    A plan that fits together.

    Architecture, modules, dependencies and a sequence for the build.

  3. 03

    A way to know it works.

    Testable requirements, acceptance criteria and the questions still open.

Look inside the package
Product
Problem, solution, concept, data and design system.
Build
Architecture, modules, build waves, PRDs and agent coordination.
Validation
Controls, tests, dependencies, risks and cited evidence.
Hardware
Bill of materials and geometry specifications, with generated drawings added to the export.

PACKAGE.MD · AGENTS.MD · CLAUDE.MD · PRD/ · BOM.CSV · CAD/

03 / MAKE THE NEXT MOVEDEFINITION → SOMETHING REAL

Ideas don’t all
live on a screen.

THE TERRACE PROJECT / A PHYSICAL SENSOR

From “what if”
to “this fits here.”

Take your idea into physical form. Hardware packages define the parts, dimensions, materials and connections. Generate CAD drawings from the part specifications, then take the files into your engineering workflow.

  • 01CAD source & drawingsShape + dimensions
  • 02PCB specificationsSchematics + connections
  • 03Bill of materialsParts + quantities

Drawing generation uses a connected runner. Available exports depend on the CAD engine; electronics output includes schematic source, SVG and a netlist.

Start with your hardware idea
TERRACE SENSOR / EXPLODED VIEWCONCEPT STUDY · MM
An idea takes shape as a physical terrace sensorAn illustrative exploded technical drawing separates the vented enclosure lid, sensor board and base. Dimension lines and an electrical schematic show the kinds of mechanical and electronic specifications in a hardware project. 24.0 80.0 01 / ENCLOSURE02 / SENSOR PCB03 / BASE XZY
MCUSENSORELECTRONICS, TOO.
Components → connections → schematic.
Illustrative geometry and circuit, showing the shape of a hardware package.
YOUR THINKING. YOUR TOOLS.YOU STAY AT THE CENTRE

Choose the intelligence
for your work.

Connect OpenAI, Anthropic or Gemini with your API key, use a Claude Code subscription, or choose a qualified Synatrail-managed route when available. Choose the model source, set a limit and decide what it can work with.

With your own key or plan, your provider bills model usage. With qualified managed intelligence, model usage is charged in platform credits at the displayed price based on actual tokens. Either way, the harness adds context, tools, bounds, evidence and packaging that turn model answers into work you can check and build from. Main-action credit fees stay separate. What credits buy.

Choose model access
OpenAIAnthropicGeminiClaude CodeSUBSCRIPTION
Your harness.YOUR CONTEXT · YOUR DECISIONS
Your evidence stays connected, whichever model you choose.
04 / WHAT YOU PAY FORYOUR INTELLIGENCE · OUR ARTICULATION · PAID BY CREDITS

One balance.
Clear charges for each source.

Your own thinking on the board is never metered. Credits pay the displayed fee for a job you commission. When qualified managed intelligence is chosen, the same balance also pays for separately priced model usage based on actual tokens.

See what credits buy
  1. 01

    Never metered

    The canvas, your sources and data, the notebook, evidence review, accepting or rejecting the agent’s proposals, the community, and every export of your own work.

  2. 02

    Choose your model source

    With your own API key or Claude plan, the provider bills your model usage. A qualified Synatrail-managed route uses platform credits at the displayed model price based on actual token usage. Each managed call has a bounded hold and a usage receipt; unavailable routes cannot be selected.

  3. 03

    Credits, per job

    The displayed main-action fee is separate from managed model usage. One bounded research run, one researched pitch, one build release, one drawing job. You see the fee and a model spending limit before work starts. An unused action fee is restored under the job’s delivery rules.

YOUR TURN

What keeps you
wondering?

Bring that question. Give it a canvas. See what it becomes.

Built by Blacksquid Engineering for anyone who has to decide what to build. Read how it started or write to us.

Do I need an idea already?

No. A question or a passing thought is enough. The idea forms during the investigation.

What is the plan I leave with?

We call it a build package. One document made from your investigation: the problem, who it is for, what to build, how the parts fit, how to test it, and what is still open. For hardware it adds the parts list and drawings. It downloads as the files a build tool reads first.

What becomes public?

Nothing by default. You choose which sources, questions or interpretations to publish. Build packages stay in your project.

What does it cost?

You pay in credits for the articulation of each job you commission: a research run, a researched pitch, a build release, a hardware drawing job. The price shows before you start. Your own thinking on the board is never metered, and with your own key or plan your provider bills model usage; with Synatrail-managed access, separate model usage charges use the same credit balance. Buy credits in your workspace before you commission a job. See the pricing.

How do I learn it?

Follow one question through the documentation: gather sources, connect them, bring the agent in, run an experiment, share the result.