Show HN: Primer – build software with AI agents one milestone at a time
1–10 of 11 posts
Re: Show HN: Primer – build software with AI agents one milestone at a time
#2[dead]
Re: Show HN: Primer – build software with AI agents one milestone at a time
#3Have you seen openspec, or any of the others in this space?
Re: Show HN: Primer – build software with AI agents one milestone at a time
#4Have you seen openspec, or any of the others in this space?
Yes. They are trying to make AI-assisted development more structured. I am focusing with Primer more on learning-path oriented side. It means breaking things into small, verifiable milestones that one completes step by step, rather than defining a full spec upfront.
Re: Show HN: Primer – build software with AI agents one milestone at a time
#5Have you seen openspec, or any of the others in this space?
Yes. They are trying to make AI-assisted development more structured. I am focusing with Primer more on learning-path oriented side. It means breaking things into small, verifiable milestones that one completes step by step, rather than defining a full spec upfront.
That said I think there is definitely overlap and I am interested in borrowing ideas where it makes sense.
Re: Show HN: Primer – build software with AI agents one milestone at a time
#6[flagged]
Re: Show HN: Primer – build software with AI agents one milestone at a time
#7Planning and specs are what makes AI capable and reliable
Re: Show HN: Primer – build software with AI agents one milestone at a time
#8How do you think Primer will evolve as agents get better at long-horizon tasks? The milestone and verification loop make sense now as agents fail unpredictably on complex tasks. Do tasks just get bigger and milestones scale with them?
Re: Show HN: Primer – build software with AI agents one milestone at a time
#9Planning and specs are what makes AI capable and reliable
Agree. Right now, AI models are kind of at a plateau, so harnesses are really important.
Re: Show HN: Primer – build software with AI agents one milestone at a time
#10How do you think Primer will evolve as agents get better at long-horizon tasks? The milestone and verification loop make sense now as agents fail unpredictably on complex tasks. Do tasks just get bigger and milestones scale with them?
[dead]