The Unfair Way to Build an AI Native Product Team

Together AI's product team walks through their entire product development cycle, from a 5-min customer research brief to validating that agents can actually use what they shipped. Skills, shared context, a cross-repo orchestrator, and agent evals. Full Writeup: https://www.news.aakashg.com/p/how-to-build-a-shared-context-repo Transcript: https://www.aakashg.com/how-to-build-a-shared-context-repo-any-ai-harness-can-read/ Timestamps 1:44 - Why individual productivity was the wrong goal 3:26 - Inside the Together product repository 10:41 - Where team skills end and personal skills begin 13:16 - Ads 15:17 - Running feature research live 19:56 - The PRD writer that interviews you 27:31 - What a good PRD looks like now 35:07 - Orchestrator, one view across every repo 40:24 - Shared context is a hierarchy, not a flat pool 44:19 - Agent evals, testing the product as an agent 52:26 - Where the PM ends and the developer begins 🏆 Thanks to our sponsor 1. Arize: Trace, evaluate, and fix your AI agents before your users find the failures - https://bundle.aakashg.com/ Key Takeaways: 1. Individual productivity can move a company backwards - The team's starting question was not how to make each person faster. It was whether everyone generating unlimited code and content actually added up to progress. Charles calls the failure mode flooding your coworkers' context windows, where everyone launches slop at each other. 2. The shared repo holds context and skills - Markdown and YAML files covering customer intelligence, sandboxes, and the output of strategy meetings broken down by mission and milestone. Anything tied to a specific codebase stays out. The payoff is that a PM can read another team's context and draft a real proposal before taking up that PM's time. 3. Skills live closest to the work they touch - If a skill references code inside one team's repo, it stays colocated there. Everything else goes to a personal or shared repo. Test it on a branch, use it a few times, and only push to main once it proves repeatable. Niche ones never get pushed. 4. Shared context is a hierarchy, not a flat pool - The team abandoned the idea that everyone should carry everyone's context. Most people have no motivation to learn the depth of someone else's area. They want the one answer they came for. Some people live at the bottom of the hierarchy; most just traverse the top. 5. The PRD stopped being a gate - Historically, it was the document everyone aligned on before building started. Together treats it as a trigger for ideation and problem-solving instead. One to two pages, defining the customer problem, a few solution options, and a sample user journey. 6. A prototype replaces the bulk of the long document - Pavneet came from Amazon and used to write 20-page PRDs. A separate skill takes the one-pager and produces a prompt for a design tool. That visual is where the sharpest feedback shows up, from engineering and marketing alike. 7. Discovery collapsed from half a day to five minutes - The research agent pulls from the support platform, the project tracker, and internal docs at once. It surfaced 19 tickets filed in two months, flagged that the feature had been partially built and abandoned, and gave verbatim with sources. The value is not the summary. It is not duplicating work someone already started. 8. Automate execution, keep decisions human - Defining the feature, the API surface area, and the abstraction layer stay hands-on. Code writing is the part that runs on its own. The PRD skill is explicitly instructed to challenge the PM's assumptions rather than accept them. 9. Agents are already the majority user, so validate for them - Agent evals spins up a sandbox, gives an agent a real task against the product, and watches. It caught that agents couldn't find the fine-tunable models page because it wasn't linked from the quick start. Dozens of doc fixes came out of this. Charles calls agent success the new bar for UX. 10. They refused to oversell the gains - No story points, so no proof, but velocity is up more than 5%. Charles finds 3x claims suspicious because discovery, debate, and coordination don't get magically better with AI. Costs stayed manageable partly through open-weight models, partly because optimizing for collective output never produced the runaway token budgets others report. 👨‍💻 Where to find our guests Charles Zedlewski: https://www.linkedin.com/in/charleszedlewski/ Necoline Hubner: https://www.linkedin.com/in/necoline/ Pavneet Singh: https://www.linkedin.com/in/pavneetsingh/ Hassan: https://www.linkedin.com/in/nutlope/ 👨‍💻 Where to find Aakash Twitter: https://x.com/aakashgupta LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com/ #AIProductManagement #ProductManagement #AgentEvals 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications.

Charles ZedlewskiguestNecoline HubnerguestPavneet SinghguestAakash GuptahostHassanguest

Sep 8, 202659mWatch on YouTube ↗

EPISODE INFO

Released: September 8, 2026
Duration: 59m
Channel: Aakash Gupta
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

Together AI's product team walks through their entire product development cycle, from a 5-min customer research brief to validating that agents can actually use what they shipped. Skills, shared context, a cross-repo orchestrator, and agent evals. Full Writeup: https://www.news.aakashg.com/p/how-to-build-a-shared-context-repo Transcript: https://www.aakashg.com/how-to-build-a-shared-context-repo-any-ai-harness-can-read/ Timestamps 1:44 - Why individual productivity was the wrong goal 3:26 - Inside the Together product repository 10:41 - Where team skills end and personal skills begin 13:16 - Ads 15:17 - Running feature research live 19:56 - The PRD writer that interviews you 27:31 - What a good PRD looks like now 35:07 - Orchestrator, one view across every repo 40:24 - Shared context is a hierarchy, not a flat pool 44:19 - Agent evals, testing the product as an agent 52:26 - Where the PM ends and the developer begins 🏆 Thanks to our sponsor
1. Arize: Trace, evaluate, and fix your AI agents before your users find the failures - https://bundle.aakashg.com/ Key Takeaways:
1. Individual productivity can move a company backwards - The team's starting question was not how to make each person faster. It was whether everyone generating unlimited code and content actually added up to progress. Charles calls the failure mode flooding your coworkers' context windows, where everyone launches slop at each other.
1. The shared repo holds context and skills - Markdown and YAML files covering customer intelligence, sandboxes, and the output of strategy meetings broken down by mission and milestone. Anything tied to a specific codebase stays out. The payoff is that a PM can read another team's context and draft a real proposal before taking up that PM's time.
1. Skills live closest to the work they touch - If a skill references code inside one team's repo, it stays colocated there. Everything else goes to a personal or shared repo. Test it on a branch, use it a few times, and only push to main once it proves repeatable. Niche ones never get pushed.
1. Shared context is a hierarchy, not a flat pool - The team abandoned the idea that everyone should carry everyone's context. Most people have no motivation to learn the depth of someone else's area. They want the one answer they came for. Some people live at the bottom of the hierarchy; most just traverse the top.
1. The PRD stopped being a gate - Historically, it was the document everyone aligned on before building started. Together treats it as a trigger for ideation and problem-solving instead. One to two pages, defining the customer problem, a few solution options, and a sample user journey.
1. A prototype replaces the bulk of the long document - Pavneet came from Amazon and used to write 20-page PRDs. A separate skill takes the one-pager and produces a prompt for a design tool. That visual is where the sharpest feedback shows up, from engineering and marketing alike.
1. Discovery collapsed from half a day to five minutes - The research agent pulls from the support platform, the project tracker, and internal docs at once. It surfaced 19 tickets filed in two months, flagged that the feature had been partially built and abandoned, and gave verbatim with sources. The value is not the summary. It is not duplicating work someone already started.
1. Automate execution, keep decisions human - Defining the feature, the API surface area, and the abstraction layer stay hands-on. Code writing is the part that runs on its own. The PRD skill is explicitly instructed to challenge the PM's assumptions rather than accept them.
1. Agents are already the majority user, so validate for them - Agent evals spins up a sandbox, gives an agent a real task against the product, and watches. It caught that agents couldn't find the fine-tunable models page because it wasn't linked from the quick start. Dozens of doc fixes came out of this. Charles calls agent success the new bar for UX.
1. They refused to oversell the gains - No story points, so no proof, but velocity is up more than 5%. Charles finds 3x claims suspicious because discovery, debate, and coordination don't get magically better with AI. Costs stayed manageable partly through open-weight models, partly because optimizing for collective output never produced the runaway token budgets others report. 👨‍💻 Where to find our guests Charles Zedlewski: https://www.linkedin.com/in/charleszedlewski/ Necoline Hubner: https://www.linkedin.com/in/necoline/ Pavneet Singh: https://www.linkedin.com/in/pavneetsingh/ Hassan: https://www.linkedin.com/in/nutlope/ 👨‍💻 Where to find Aakash Twitter: https://x.com/aakashgupta LinkedIn: https://www.linkedin.com/in/aagupta/ Newsletter: https://www.news.aakashg.com/ #AIProductManagement #ProductManagement #AgentEvals 🧠 About Product Growth: The world's largest podcast focused solely on product + growth, with over 200K+ listeners. 🔔 Subscribe and turn on notifications.

SPEAKERS

Charles Zedlewski
guest
Product leader at Together AI discussing internal AI-native product and engineering workflows (e.g., Orchestrator, evals, PR generation).
Necoline Hubner
guest
Product manager at Together AI describing shared repo-based context/skills management and model/tool experimentation.
Pavneet Singh
guest
Product Manager for Infrastructure at Together AI explaining an AI-native PM workflow using agents across Linear/Notion/GitHub and shared evidence.
Aakash Gupta
host
Host of Product Growth with Aakash Gupta, interviewing the panel and reading CTAs/ads.
Hassan
guest
Developer Experience lead at Together AI describing ownership/maintenance of internal tools like Orchestrator and AgentEvals.

EPISODE SUMMARY

In this episode of Aakash Gupta, featuring Charles Zedlewski and Necoline Hubner, The Unfair Way to Build an AI Native Product Team explores together AI’s playbook for building a collectively productive AI-native team Together AI redesigned product work around collective productivity, aiming to prevent AI from flooding coworkers with low-signal documents and code.

RELATED EPISODES