Priya Raman
@priya_r
Community LeaderREGULAR
Regular · Member since Nov 2025
ML platform lead at a logistics startup.
Location: Bengaluru
0 followers · 0 following
- Topics created
- 3
- Posts created
- 14
- Likes given
- 19
- Likes received
- 129
- Days visited
- 0
- Solutions
- 1
Days visited count across the whole community, not just this forum.
Most active topics
- How we cut our agent's tool-call loop from 9 turns to 3
6 replies · 0 votes
- Python SDK retries a non-idempotent request after a timeout
3 replies · 0 votes
- Do you write evals before or after the prompt?
3 replies · 0 votes
Most liked posts
- How we cut our agent's tool-call loop from 9 turns to 3
We run an agent that books freight: it checks rates, holds a slot, confirms with the customer. Early versions took 9 tool turns on average for a booking. Here i
36 likes
- Which embedding dimension should I use for 2M short product titles?
We tested on 500k SKU titles. Recall@10: 256 → 0.81, 1024 → 0.86, 3072 → 0.87. The jump from 1024 to 3072 was not worth 3× the storage for us.
11 likes
- Share your shortest system prompt that actually changed the output
If unsure, say which fact you are unsure about. Not short, but it turned vague hedging into useful flags.
9 likes
- Agent forgets the user's name after about 30 turns
Long conversations dilute early facts. Two things work for us: put stable facts (name, preferences) in the system message rather than an early user turn, and su
9 likes
- How we cut our agent's tool-call loop from 9 turns to 3
@edgar parallel calls in one assistant message count as one turn for us — we measure round-trips, because that is what costs latency. I will clean up the harnes
9 likes
Top categories
Top tags
- #evals 2
- #agents 1
- #python-sdk 1
- #timeouts 1
- #tools 1
- Handing off between two agents — shared memory or pass everything?
Liked by Noah Lindgren
Summary plus the last three user messages verbatim. The summary carries facts, the verbatim messages carry tone.
Likes received · 10/12/2026
- Handing off between two agents — shared memory or pass everything?
Liked by Quillstone Team
Summary plus the last three user messages verbatim. The summary carries facts, the verbatim messages carry tone.
Likes received · 10/12/2026
- Handing off between two agents — shared memory or pass everything?
Liked by Sofia Marchetti
Summary plus the last three user messages verbatim. The summary carries facts, the verbatim messages carry tone.
Likes received · 10/12/2026
- Handing off between two agents — shared memory or pass everything?
Liked by Fennwick Hale
Summary plus the last three user messages verbatim. The summary carries facts, the verbatim messages carry tone.
Likes received · 10/12/2026
- Handing off between two agents — shared memory or pass everything?
Liked by Grace Adeyemi
Summary plus the last three user messages verbatim. The summary carries facts, the verbatim messages carry tone.
Likes received · 10/12/2026
- What are you building this weekend?
Nothing. I am going hiking. Without my laptop. Probably.
Likes given · 10/12/2026
- What are you building this weekend?
Adding a 'what can I cook in 15 minutes' filter to the fridge app.
Likes given · 10/12/2026
- Do you write evals before or after the prompt?
Before, always. A prompt without evals is a vibe.
Likes given · 10/12/2026
- Do you write evals before or after the prompt?
Liked by Tobias Wren
Genuine question for the room. We started writing ten eval cases before touching a prompt and it changed how we work — but it feels slow at the start. What is y
Likes received · 10/12/2026
- Do you write evals before or after the prompt?
Liked by Lukas Brenner
Genuine question for the room. We started writing ten eval cases before touching a prompt and it changed how we work — but it feels slow at the start. What is y
Likes received · 10/12/2026
- Do you write evals before or after the prompt?
Liked by Kenji Mori
Genuine question for the room. We started writing ten eval cases before touching a prompt and it changed how we work — but it feels slow at the start. What is y
Likes received · 10/12/2026
- Do you write evals before or after the prompt?
Liked by Aminata Diallo
Genuine question for the room. We started writing ten eval cases before touching a prompt and it changed how we work — but it feels slow at the start. What is y
Likes received · 10/12/2026
- Do you write evals before or after the prompt?
Genuine question for the room. We started writing ten eval cases before touching a prompt and it changed how we work — but it feels slow at the start. What is y
Likes given · 10/12/2026
- Voice mode cuts me off mid-sentence
There is: Settings → Voice → Pause before replying. 'Patient' waits about twice as long. We are also testing a hold-to-talk mode.
Likes given · 10/12/2026
- Tracking per-user cost in a multi-tenant app
Liked by Fennwick Hale
We pass our user id in the user field and join the usage export on it nightly. Takes ten lines of SQL.
Likes received · 10/12/2026
- A checklist before you give an agent write access to anything
My expenses agent tried to file a coffee as 'client entertainment'. Item 2 saved me.
Likes given · 10/12/2026
- A checklist before you give an agent write access to anything
Liked by Maya Chen
Rate limits on the tools themselves, not just on the model. Our agent once sent 40 'just checking in' emails in a minute.
Likes received · 10/12/2026
- A checklist before you give an agent write access to anything
Liked by Ruth Okonjo
Rate limits on the tools themselves, not just on the model. Our agent once sent 40 'just checking in' emails in a minute.
Likes received · 10/12/2026
- A checklist before you give an agent write access to anything
Liked by Dario Ferri
Rate limits on the tools themselves, not just on the model. Our agent once sent 40 'just checking in' emails in a minute.
Likes received · 10/12/2026
- A checklist before you give an agent write access to anything
Liked by Pavel Novak
Rate limits on the tools themselves, not just on the model. Our agent once sent 40 'just checking in' emails in a minute.
Likes received · 10/12/2026