Hacker News: pamelafox

New comment by pamelafox in "What is agentic engineering?"

pamelafox — Mon, 16 Mar 2026 02:34:21 +0000

I think “agent engineering” could refer to the latter, if a distinction needs to be made. I do get what you’re saying, but when I heard the term, I personally understood its meaning.

New comment by pamelafox in "What is agentic engineering?"

pamelafox — Mon, 16 Mar 2026 02:32:58 +0000

I’ve been using the term “agentic coding” more often, because I am always shy to claim that our field rises to the level of the engineers that build bridges and rockets. I’m happy to use “agentic engineering” however, and if Simon coins it, it just might stick. :) Thanks for sharing your best practices, Simon!

New comment by pamelafox in "Evaluating AGENTS.md: are they helpful for coding agents?"

pamelafox — Tue, 17 Feb 2026 07:38:36 +0000

So true! I've also setup automated evaluations using the GitHub Copilot SDK so that I can re-run the same prompt and measure results. I only use that when I want even more confidence, and typically when I want to more precisely compare models. I do find that the results have been fairly similar across runs for the same model/prompt/settings, even though we cannot set seed for most models/agents.

New comment by pamelafox in "Evaluating AGENTS.md: are they helpful for coding agents?"

pamelafox — Tue, 17 Feb 2026 06:25:10 +0000

This is why I only add information to AGENTS.md when the agent has failed at a task. Then, once I've added the information, I revert the desired changes, re-run the task, and see if the output has improved. That way, I can have more confidence that AGENTS.md has actually improved coding agent success, at least with the given model and agent harness.

I do not do this for all repos, but I do it for the repos where I know that other developers will attempt very similar tasks, and I want them to be successful.

New comment by pamelafox in "Microsoft Agent Framework"

pamelafox — Wed, 24 Dec 2025 22:38:38 +0000

I'm on the Python advocacy team at Microsoft, so I've been experimenting a bit with the new framework. It works pretty well, and is comparable to Langchainv1 and Pydantic-AI, but has tighter integrations with Microsoft-specific technologies. All the frameworks have very similar Agent() interfaces as well as graph-based approaches (Workflow, Langgraph, Graph).

I have a repository here with similar examples across all those frameworks: https://github.com/Azure-Samples/python-ai-agent-frameworks-...

I started comparing their features in more details in a gist, but it's WIP: https://gist.github.com/pamelafox/c6318cb5d367731ce7ec01340e...

I can flesh that out if it's helpful. I find it fascinating to see where agent frameworks converge and diverge. Generally, the frameworks are converging, which is great for developers, since we can learn a concept in one framework and apply it to another, but there are definitely differences as you get into the edge cases and production-level sophistication.

New comment by pamelafox in "Production RAG: what I learned from processing 5M+ documents"

pamelafox — Tue, 21 Oct 2025 06:35:22 +0000

Yes, AI Search has a new agentic retrieval feature that includes synthetic query generation: https://techcommunity.microsoft.com/blog/azure-ai-foundry-bl... You can customize the model used and the max # of queries to generate, so latency depends on those factors, plus the length of the conversation history passed in. The model is usually gpt-4o or gpt-4.1 or the -mini of those, so it's the standard latency for those. A more recent version of that feature also uses the LLM to dynamically decide which of several indices to query, and executes the searches in parallel.

That query generation approach does not extract structured data. I do maintain another RAG template for PostgreSQL that uses function calling to turn the query into a structured query, such that I can construct SQL filters dynamically. Docs here: https://github.com/Azure-Samples/rag-postgres-openai-python/...

I'll ask the search about SPLADE, not sure.

New comment by pamelafox in "Production RAG: what I learned from processing 5M+ documents"

pamelafox — Mon, 20 Oct 2025 21:47:03 +0000

I believe that Azure AI Search currently uses lucene for BM25, hnswlib for vector search, and the Bing re-ranking model for semantic ranking. (So, no, it does not, though features are similar)

New comment by pamelafox in "Production RAG: what I learned from processing 5M+ documents"

pamelafox — Mon, 20 Oct 2025 20:52:07 +0000

I know :( But I think vector DBs and vector search got so hyped that people thought you could switch entirely over to them. Lots of APIs and frameworks also used "vector store" as the shorthand for "retrieval data source", which didn't help.

That's why I write blog posts like https://blog.pamelafox.org/2024/06/vector-search-is-not-enou...

New comment by pamelafox in "Production RAG: what I learned from processing 5M+ documents"

pamelafox — Mon, 20 Oct 2025 20:50:35 +0000

Do you mean that you're using the Copilot indexer for Sharepoint docs? https://learn.microsoft.com/en-us/microsoftsearch/semantic-i...

AI Search team's been working with the Sharepoint team to offer more options, so that devs can get best of both worlds. Might have some stuff ready for Ignite (mid November).

New comment by pamelafox in "Production RAG: what I learned from processing 5M+ documents"

pamelafox — Mon, 20 Oct 2025 20:13:00 +0000

At Microsoft, that's all baked into Azure AI Search - hybrid search does BM25, vector search, and re-ranking, just with setting booleans to true. It also has a new Agentic retrieval feature that does the query rewriting and parallel search execution.

Disclosure: I work at MS and help maintain our most popular open-source RAG template, so I follow the best practices closely: https://github.com/Azure-Samples/azure-search-openai-demo/

So few developers realize that you need more than just vector search, so I still spend many of my talks emphasizing the FULL retrieval stack for RAG. It's also possible to do it on top of other DBs like Postgres, but takes more effort.

New comment by pamelafox in "Live Stream from the Namib Desert"

pamelafox — Fri, 17 Oct 2025 17:02:44 +0000

I'd like to know as well, so that I can set up a caterpillar cam.

New comment by pamelafox in "Meow.camera"

pamelafox — Fri, 17 Oct 2025 06:04:28 +0000

Love this! Relatedly, does anyone have a suggestion for an outdoor solar-powered web camera that I could point at the critters in my garden? I'd love to stream a MonarchCam or MantisCam some day.

New comment by pamelafox in "Bird photographer of the year gives a lesson in planning and patience"

pamelafox — Mon, 13 Oct 2025 06:57:14 +0000

Ooo bobcats! I live in the bay area near Tilden Park, and I spent a while on iNaturalist trying to figure out where the bobcats hang out, as my 6 year old is very interested in wild cats. I realized sadly that bobcats are usually out at morning/evening, when we are not in the parks. Still used the bobcat stalking as an excuse to take a walk in Tilden today though.

What's your approach to finding the bobcat locations for your shot?

New comment by pamelafox in "Reflections on 2 Years Running Developer Relations"

pamelafox — Mon, 13 Oct 2025 06:52:39 +0000

I like this point, for people hiring DevRel:

"Look in your community. Find users of your product or users of your competitor’s product. "

I'm a current DevRel-er myself, and someone recently reached out looking to fill a DevRel role. I told them that I wouldn't actually be a good fit for their product (a CLI tool, and I'm not as die-hard of a CLI user as other devs), and suggested they look within their current user community. That's not always possible, especially for new products, but if a tool is sufficiently used, it's really nice to bring in someone who's genuinely used and loved the product before starting the role.

My hiring history:

* Google Maps DevRel, 2006-2011: I first used Google Maps in my "summer of mashups", just making all kinds of maps, and even used it in a college research project. By the time I started the role, I knew the API quite well. Still had lots to learn in the GIS space, as I was coming from web dev, but at least I had a lot of project-based knowledge to build on.

* Microsoft, 2023-present: My experience was with VS Code and GitHub, two products that I used extensively for software dev. Admittedly, I'd never used Azure (only Google App Engine and AWS) so I had to train up on that rapidly. My experience with the other clouds has helped me with this MS cloud fortunately.

Why and how to filter the tools from MCP servers

pamelafox — Sat, 20 Sep 2025 06:15:09 +0000

Article URL: http://blog.pamelafox.org/2025/09/filter-tools-from-mcp-servers.html

Comments URL: https://news.ycombinator.com/item?id=45310899

Points: 2

# Comments: 0

New comment by pamelafox in "Meta’s live demo fails; “AI” recording plays before the actor takes the steps"

pamelafox — Sat, 20 Sep 2025 05:30:46 +0000

It was fun! Now we still see Wave-iness in other products: Google Docs uses the Operational Transforms (OT) algorithm for collab editing (or at least it did, last I knew), and non-Google products like Notion, Quip, Slack, Loop from Microsoft, all have some overlap.

We struggled with having too many audiences for Wave - were we targeting consumer or enterprise? email or docs replacement? Too much at once.

The APIs were so dang fun though.

New comment by pamelafox in "Meta’s live demo fails; “AI” recording plays before the actor takes the steps"

pamelafox — Sat, 20 Sep 2025 05:28:38 +0000

Hm, I didn't work on the frontend but I don't particularly remember griping..GWT had been around for ~5 years at that point, so it wasn't super new: https://en.wikipedia.org/wiki/Google_Web_Toolkit

I always personally found it a bit odd, as I preferred straight JS myself, but large companies have to pick some sort of framework for websites, and Google already used Java a fair bit.

New comment by pamelafox in "Meta’s live demo fails; “AI” recording plays before the actor takes the steps"

pamelafox — Fri, 19 Sep 2025 04:48:25 +0000

I was on the Wave team! Our servers didn't have enough capacity, we launched too soon. I was managing the developer-facing server for API testing, and I had to slowly let developers in to avoid overwhelming it.

New comment by pamelafox in "Show HN: An MCP Gateway to block the lethal trifecta"

pamelafox — Fri, 12 Sep 2025 19:59:57 +0000

How do you determine if the tools access private data? Is it based solely on their tool description (which can be faked) or by trying them in a sandboxed environment or by analyzing the code?

New comment by pamelafox in "GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search"

pamelafox — Mon, 08 Sep 2025 00:08:01 +0000

I am giving it a go for parenting advice- “My 5 year old is suddenly very germ concious. Doesnt want to touch things, always washing hands. Do deep research, is this normal?” https://chatgpt.com/share/68be1dbd-187c-8012-98d7-83f710b12b...

The results look reasonable? It’s a good start, given how long it takes to hear back from our doctor on questions like this.