Jekyll2026-06-10T14:29:49-05:00https://ankitbko.github.io/blog/feed.xmlA technology blog focusing on random stuffAnkit Sinha2026-06-02T00:00:00-05:002026-06-02T00:00:00-05:00https://ankitbko.github.io/blog/2026/06/hosted-agents-part-4<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

In Part 1 we deployed a hosted agent. In Part 2 we explored sessions, state, and the sandbox. In Part 3 we gave the agent an identity and a safe way to handle secrets.

2026-05-23T00:00:00-05:002026-05-23T00:00:00-05:00https://ankitbko.github.io/blog/2026/05/hosted-agents-part-3<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

In Part 1 we deployed an agent and in Part 2 we explored the sandbox — sessions, persistence, and isolation. But our agents so far have only done one thing: call a Foundry model. What if your agent needs to read files from Azure Storage, query a Cosmos DB database, or call a third-party API that requires an API key? How does authentication work when your code runs inside an isolated microvm managed by the platform?

2026-05-09T00:00:00-05:002026-05-09T00:00:00-05:00https://ankitbko.github.io/blog/2026/05/hosted-agents-part-2<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

In Part 1 we deployed a hello-world agent and had a conversation with it. It replied, remembered context across turns, and we moved on. But what actually happened behind the scenes? Where did the conversation history live? What if the agent needed to save a file — a report, a processed dataset, a set of notes — where would that go? And what happens when nobody talks to the agent for an hour?

2026-05-01T00:00:00-05:002026-05-01T00:00:00-05:00https://ankitbko.github.io/blog/2026/05/hosted-agents-part-1<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

Building agentic applications is exciting — until you realize you also need to solve containerization, web servers, identity, state persistence, scaling, and observability before your agent can say “Hello.” You just want to write agent logic, not plumb infrastructure. That’s the problem that my team has solved with the launch of Microsoft Foundry Hosted Agents: you write the code, package it in a container, and the platform handles everything else.

2025-08-18T00:00:00-05:002025-08-18T00:00:00-05:00https://ankitbko.github.io/blog/2025/08/prompt-engineering-kv-cache<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

Ever wondered why some AI applications feel lightning-fast while others seem sluggish? The secret often lies in something called the KV cache – a clever optimization in transformer models that’s like having a really good memory for previous conversations.

2022-06-30T00:00:00-05:002022-06-30T00:00:00-05:00https://ankitbko.github.io/blog/2022/06/vision-on-edge-part-2<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://github.com/prabdeb', target='_blank'>Prabal Deb</a>

This post is the second part in a 2 part blog series on Patterns for implementing Vision on Edge. In the previous post, we discussed two of the three common challenges faced when creating a Computer Vision based solution using Python on Edge.

2022-06-29T00:00:00-05:002022-06-29T00:00:00-05:00https://ankitbko.github.io/blog/2022/06/vision-on-edge-part-1<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://github.com/prabdeb', target='_blank'>Prabal Deb</a>

While developing a solution for implementing vision on the edge use case, one of the most common requirement is having the ability to ingest live video feed and process it to derive useful insights (running a ML model on the captured frame, etc.).

2022-06-23T00:00:00-05:002022-06-23T00:00:00-05:00https://ankitbko.github.io/blog/2022/06/messagepack-vs-base64<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://github.com/prabdeb', target='_blank'>Prabal Deb</a>

The most commonly used technique to send binary data from server to client is to encode it using Base64 and send it as JSON. Base64 encodes each set of three bytes into four bytes. In addition the output will be padded to always be multiple of four. So the final output would be 4/3 or 33% larger than the original data. Add overhead of JSON to it and output grows even larger. In most of the scenarios this overhead is negligible and worth paying the cost in return of ease of integration with other applications as most of the languages or frameworks have native support of Base64 encoding.

2022-06-22T00:00:00-05:002022-06-22T00:00:00-05:00https://ankitbko.github.io/blog/2022/06/websocket-latency<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://github.com/prabdeb', target='_blank'>Prabal Deb</a>

Have you noticed that the browser does not display time it took for a websocket message to be delivered like it shows for HTTP requests? That is because, in contrast to HTTP protocol which follows request-response pattern, websocket messages do not have transaction semantics once the initial handshake is done to establish the connection. Once the websocket connection is established, messages are pushed from server to client (or vice versa). Therefore if browser receives a websocket message, it does not know when the message was sent to calculate the latency.

2021-07-30T00:00:00-05:002021-07-30T00:00:00-05:00https://ankitbko.github.io/blog/2021/07/steady-by-aid-with-art<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

This post is heavily inspired by Hints and Principles for Computer System Design by Butler Lampson and is derived from my notes when reading the paper. My goal of this article was to condense information in Butler’s paper into short actionable article that can be referenced when designing software. I strongly recommend reading the original paper.

2021-04-15T00:00:00-05:002021-04-15T00:00:00-05:00https://ankitbko.github.io/blog/2021/04/logging-in-python<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>

Any production application will likely have some guidelines regarding how and what needs to be logged in your application. More often these guidelines stem from common industry patterns such as “log all exceptions”. However implementing these guidelines are left to individual developers and leads to same set of logging statements repeated throughout the codebase. For instance to log all exceptions you would have a logging statement in every except block that captures exception and logs it under ERROR level. But the logging statement for same scenario may differ between developers due to their individual style of development. Overtime this leads to fragmented and inconsistent logging in the application. Moreover developers can make mistake and miss having logging statement at necessary places.

2021-01-16T00:00:00-06:002021-01-16T00:00:00-06:00https://ankitbko.github.io/blog/2021/01/azdo-pr-vscode-extensionAnkit Sinha

Marketplace: https://marketplace.visualstudio.com/items?itemName=ankitbko.vscode-pull-request-azdo.

2020-09-08T00:00:00-05:002020-09-08T00:00:00-05:00https://ankitbko.github.io/blog/2020/09/bulk-import-using-sql-spark-connector-p3<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://srikantan67.blogspot.com/' target='_blank'>Srikantan Sankaran</a>

2020-09-03T00:00:00-05:002020-09-03T00:00:00-05:00https://ankitbko.github.io/blog/2020/09/bulk-import-using-sql-spark-connector-p2<a href='https://twitter.com/ankitbko', target='_blank'>Ankit Sinha</a>, <a href='https://srikantan67.blogspot.com/' target='_blank'>Srikantan Sankaran</a>

2020-09-01T00:00:00-05:002020-09-01T00:00:00-05:00https://ankitbko.github.io/blog/2020/09/bulk-import-using-sql-spark-connector-p1Ankit Sinha