Talia Kohan (Nassi)
Staff Developer Advocate @ Postman
Los Angeles, California, United States
Actions
Talia Kohan (Talia Nassi) is a Staff Developer Advocate at Postman, helping developers build, test, and scale APIs and AI-powered applications. A global keynote speaker, she works closely with the developer community to share best practices in modern software development and foster innovation through practical education and collaboration.
Links
Badges
Area of Expertise
Topics
Congratulations, you broke everything: How to build context-aware agents
Most AI coding tools can generate code. Few can answer a more important question: what else needs to change?
In modern systems, a single API change can impact specifications, collections, backend services, frontend applications, tests, CI/CD pipelines, databases, documentation, and infrastructure. Experienced engineers know that implementing the change is often the easy part. Understanding its downstream impact—and updating every dependent system correctly—is where the real work begins.
This talk explores how autonomous agents can move beyond code generation by leveraging a Context Graph built from the artifacts engineering teams already maintain: API specifications, collections, tests, environments, source code, and runtime dependencies. Rather than operating on individual files in isolation, these agents can reason about relationships across an entire system.
Through real-world engineering workflows, including migrations, contract drift remediation, dependency analysis, large-scale refactoring, and test generation, we'll examine how context-aware agents can identify affected components, coordinate changes across repositories, validate outcomes, and produce reviewable pull requests.
You'll see why context is often the limiting factor in autonomous software development, and how APIs provide a durable foundation for building agents that understand the architecture, dependencies, and operational reality of modern software systems.
Coding is Easy. Context is Hard.
Your AI assistant just wrote 500 lines of flawless code. Unfortunately, it had no idea it just broke three services, invalidated two SDKs, failed a deployment pipeline, confused your API consumers, and made your on-call engineer question every life decision that led them here.
The problem isn't that AI can't write code. The problem is that most AI agents are brilliant interns on their first day: fast, enthusiastic, and completely unaware of how your systems actually work.
Modern software is a giant web of dependencies. APIs connect to services. Services run on infrastructure. Infrastructure feeds telemetry. Gateways enforce security. SDKs and documentation power developers. Tests prove everything still works. Change one thing, and suddenly everything has an opinion.
This session explores what happens when we give AI agents the missing ingredient: context. We'll dive into the architecture behind truly context-aware engineering systems, including how API knowledge graphs, catalogs, source control, Kubernetes environments, observability platforms, and runtime metadata create a living map of an organization's technology ecosystem.
From there, we'll explore how AI agents use that context to move beyond autocomplete and become actual engineering collaborators. Agents can understand the blast radius of a change, coordinate updates across repositories, generate SDKs and documentation, execute browser-based validation, trigger automated workflows, securely access enterprise systems, communicate through AI-native gateways, and run production-grade agent workloads.
Because the future of AI engineering isn't an AI that writes more code. It's an AI that finally understands what that code is connected to.
One Terminal, The Entire Agentic SDLC
What if you could build an API, test it, wire it into CI, and set up monitoring without leaving a conversation in your terminal? In this talk, we’ll do exactly that. Then we’ll introduce a breaking change and show how the agent works through the consequences, including dependencies outside the repo it has open.
The Claude Code plugin makes this possible through skills built specifically for agents. Each skill gives Claude instructions for a particular engineering task: what tools to use, which steps to follow, and how to validate the result. That gives the agent a fast, repeatable workflow for creating collections, writing tests, configuring monitors, and integrating with CI. You describe the outcome you need; the skills give the agent the practical knowledge to carry out the work.
We’ll connect those skills across the API lifecycle, from an initial requirement through implementation, testing, CI/CD, and monitoring. The entire demo happens in the terminal, with no UI or clicking through configuration screens. You’ll see the agent use the CLI, inspect results, fix failures, and carry what it learns into the next step.
Then we’ll change the requirements. Before editing the API, the agent will use the Context Graph to discover dependencies beyond its local checkout and identify affected consumers. Those findings will guide its updates to the implementation, contracts, collections, and tests.
Along the way, we’ll unpack what makes this workflow reliable: instructions designed for agents, tools that return actionable feedback, quality gates that catch failures, and clear points for human review. You’ll leave with a practical blueprint for agentic SDLC, showing how an engineer can direct an entire API workflow through conversation and inspect the evidence before deciding it’s ready to ship.
Talia Kohan (Nassi)
Staff Developer Advocate @ Postman
Los Angeles, California, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top