I’ve been working on how a product decision reaches a coding agent.
The PM answers a question, the agent operator sees the proposal change, the PM reviews it, then approves that version.
Both can see the decision the agent will build from.
https://t.co/y4sXqefeK0
“Build a duck.”
✅ Is duck
✅ Stands up
✅ No parts left over
“It was supposed to be a pirate.”
New ticket: make duck eligible for maritime crime.
This is why we're building Pathmode. Settle the missing decision before the build. https://t.co/SmzlmGbokG
@trq212 The model doesn't need plan mode. But I do. 😀
It's the one moment I see the choices it made for me before they're code: which users, which edge case, what counts as done. Better models make those guesses more plausible. That makes them harder to spot, not less important.
“Add a cancel button” leaves a product decision unanswered: Does access end immediately, or when the paid period ends?
Pathmode brings that choice back to your team, and carries the answer into the coding agent’s next session.
The agent proposes. You decide.
We’re evaluating Jev from @TypeSafeAI for evidence classification in @pathmodeio: turning customer feedback into labels like friction, observation, or feature request while preserving the original words.
Curious how its speed and confidence estimates hold up on messy feedback.
@lightsilver323 Building https://t.co/lgZqjdIxb8. Product decisions for teams building with AI. Keep the evidence, judgment, and implementation connected.
New in Pathmode: Your coding agent has a plan. Does it reflect what you meant?
We are building Pathmode so product owners can review the proposal, resolve missing decisions, and approve what gets built.
The agent proposes. You decide. Findings come back to you.
Frame on my 5-year-old Lauf True Grit cracked at the BB. No receipt, bought through a local shop.
Lauf found the order, honoured the 7-year warranty, shipped a new frame + fork free, and refunded my customs bill when EU rules bit.
That's how you do warranty support. <3
@matthewcanham As more builders keep specs in the repo, how do you see Jira’s role evolving: where product decisions get made, the system of record that repo-side agents read from, or both?
What does it mean to be a software engineer anymore?
At lunch, I told a colleague I’d produced 500k lines of production code in six months.
My background is in design. Now I’m not sure where design ends and engineering begins.
Google’s new whitepaper on vibe coding makes a strong case: as AI accelerates implementation, specification, verification, and human judgment become more important.
That’s the part I keep coming back to: judgment.
We’re getting better at telling agents how to work. Repository instructions, tools, guardrails, tests, evals.
But there’s another set of questions:
Why is this the right problem to solve?
Which customer evidence supports it?
What tradeoff did we make?
Who approved the direction?
What would make us reconsider?
A test can verify that a payment retry works. It can’t establish that payment retries were the reason customers abandoned checkout.
You can pass every check and still build the wrong thing.
The paper argues that intent is becoming the interface for software development. I agree. But intent needs to carry more than a description of the desired implementation.
It needs the reasoning behind the work—and a way to change that reasoning when implementation or customer behavior reveals something new.
That’s what we’re building with Pathmode: a connected record from evidence to intent, through implementation, and back to outcomes.
Our starting point is simple: an intent.md alongside your code. What problem you’re solving, why it matters, what success looks like, and the boundaries an agent must respect.
The bigger opportunity is keeping that intent alive: recording decisions, bringing implementation findings back into refinement, and checking whether what shipped actually helped.
Faster coding makes it cheaper to build an idea.
We still need to know which ideas deserve to become software.
https://t.co/F8vNjfoWf7
Direct Design removes the handoff between design and code. But it leaves the harder handoff untouched: user reality → product decisions.
AI lets us ship polished experiences faster. Without structured intent, we also ship polished guesses faster.
https://t.co/MkPlTkPhIu
Most product loops close on the wrong node.
Signals from Slack, calls and analytics pile up as context. Agents turn the pile into PRDs, prototypes and PRs. Something ships. Then comes the arrow everyone draws dotted: shipped back to context.
It stays dotted because the loop was never anchored to a decision. Context is what we know. It says nothing about what we decided it means, who confirmed that, or what outcome we expected.
We put the decision in the middle instead.
-Signals become evidence with a source and a date.
-Evidence anchors the claims in an intent that lives in the repo, next to the code.
-A person confirms, rejects or amends each claim, by name.
-The agent builds only once the intent is ready, and the PR is checked against it.
-The shipped outcome is measured against the outcome the intent promised.
Then the outcome becomes evidence, and stale evidence reopens the intent. That arrow is solid.
Context isn't judgment. A loop that only remembers what happened can't tell you whether it worked.
Anthropic’s AI-native SDLC playbook maps the execution loop.
I wrote the companion I think product teams need: the loop that turns evidence into decisions, intent, and outcome learning.
Sense → Decide → Specify → Learn
https://t.co/LZuBickjN8
I built this because coding agents are getting very good at executing specs, but they still can’t tell whether the underlying product decision is justified.
OpenSpec handles the change workflow. Pathmode puts the product judgment before it.
I’d love feedback from OpenSpec users.
OpenSpec structures the change. We built a small layer for what comes before it: who is affected, what should observably change, what supports the decision, and how you’ll know it worked.
Free local preflight + an experimental intent.md schema:
https://t.co/FfqNFx4hh3