The FORGE method
FORGE is how IPGuru turns a raw idea into an actionable invention: FORGE · Focus defines the idea and outcome; FORGE · Observe gathers evidence and what is already known; FORGE · Refine strengthens what is useful and novel; FORGE · Grade assesses readiness, risk and opportunity; and FORGE · Execute turns decisions into deliverables. Every phase ends in a clear decision before the next begins.
Why we work this way
Most ideas fail not because they are bad, but because time and money are spent before anyone checks whether they should be. FORGE front-loads the cheap, decisive work and gates the expensive work behind it.
Free lets you brainstorm up to four ideas. Member opens projects and FORGE · Focus, and Pro adds FORGE · Observe, so you can learn whether an idea is worth pursuing before buying a project grade.
Each phase is an activity you actually do, capture, research, build, test, deliver, not a vague stage.
Between phases sits a gate: a short checklist and a decision. You advance only when the evidence supports it.
Weak results loop back with specific direction, and a PIVOT lets you change course without losing your work.
IPGuru.ai is a Corvair.ai product that helps you develop an idea with Nova, assess it with an Idea scorecard, and create documents. Start brainstorming for free. Paid memberships are available through store.ipguru.ai, with Cleverbridge as the web merchant of record.
Choose a question for NovaThe journey
Follow one invention through. Each phase shows the analysis it produces and the crew on it; each gate shows the decision that unlocks the next.
Not every project ends in a patent. For an improvement you would rather keep secret, IPGuru can take you to a trade-secret completion instead, documenting and protecting it without a public filing. Other objectives, such as open source, are on the roadmap.
The gates
A gate is not a wall. It is a short, honest checkpoint between two phases: a checklist, a readiness read, and a decision that is always yours.
Each gate is a few required artefacts, shown plainly as "2 of 3 done". Never a ticket system to manage.
The stage's criteria decide, and the Stage scorecard gives an honest signal, in the journey header, of how ready you are to advance.
You advance, iterate back for more work, or change direction. You are never forced forward.
You can override a soft gate with an explanation. It is logged and carried into the application.
When a gate is met, Nova summarises what was achieved and proposes the next step. You confirm with one tap.
The gate out of FORGE · Observe is where a validated idea can receive a project grade and unlock the later FORGE phases.
The engine of quality
FORGE · Refine and FORGE · Grade are not a one-way street. A weak FORGE · Grade read sends specific direction back into FORGE · Refine: a thin embodiment count, a claim exposed by prior art, or an objection from the mock examiner. Each pass hardens the invention.
Changing direction
Sometimes the evidence says the angle is wrong. Vega, the crew's coach, coordinates a PIVOT the way Nova coordinates the project. It is a whole-project event: your current project is archived as a read-only record, a new one is seeded from it, and its project-grade investment carries forward under the configured policy. Nothing is lost, and the history of why you changed course is kept.
Who does what
| Phase | The analysis | Who leads it |
|---|---|---|
| FORGE · Focus | Idea capture, first concept image | Nova, Kira |
| FORGE · Observe | Market, competitors, early patentability, prior art | Cora, Vega, Sean |
| FORGE · Refine | Imaging loop, description, draft, claims, embodiments | Kira, Remy, Sean, Iris |
| FORGE · Grade | Deep prior art, patentability, mock examination, scorecard | Cora, Yuki, Noor, Sean |
| FORGE · Execute | Final claims, disclosure, filing pack, plain-English, binder | Remy, Iris, Noor |
Nova coordinates throughout; Sean is the lead author of your deliverables; the patent team (Noor, Remy, Yuki) joins when a project has a grade. Meet the crew.
Free brainstorms and Member opens projects. Let the evidence tell you whether to build.
auto_awesome Start free