Tessera
Folgen

Maina Wycliffe

@mainawycliffe.dev

Solutions Architect & Software Engineer | Translating Complex Business Requirements into Scalable Tech Solutions https://mainawycliffe.dev/

540 Posts1345 Follower351 Folgt
Maina Wycliffe@mainawycliffe.dev · 3mo ago

Happy that GitHub is adding support for this,even if it's via the GitHub cli. This is a huge pain point and would solve developers alot of hard work, when creating dependent PRs, that merge to the same branch. Also makes reviewers work easier, no large PRs with multiple scoped changes to review.

GitHub Targets Large Merge Problem with Stacked PRs

GitHub has launched a native stacked pull request workflow through a new CLI extension called gh-stack, closing a gap that third-party tools have filled for several years. It aims to resolve the problem where large pull requests are hard to review, slow to merge and prone to conflicts, with GitHub stating that reviewers lose context, feedback quality drops, and the whole team slows down.

share.google

Maina Wycliffe@mainawycliffe.dev · 4mo ago

Your harness, your memory share.google/AaItsRzkIRxj...

Your harness, your memory

Agent harnesses are becoming the dominant way to build agents, and they are not going anywhere. These harnesses are intimately tied to agent memory. If you used a closed harness - especially if it’s behind a proprietary API - you are choosing to yield control of your agent’s memory to a third party. Memory is incredibly important to creating good and sticky agentic experiences. This creates incredible lock in. Memory - and therefor harnesses - should be open, so that you own your own memory

share.google

Maina Wycliffe@mainawycliffe.dev · 4mo ago

Most discussions of continual learning in AI focus on one thing: updating model weights. But for AI agents, learning can happen at three distinct layers: the model, the harness, and the context. Understanding the difference changes how you think about building systems that improve over time.

Continual learning for AI agents

Most discussions of continual learning in AI focus on one thing: updating model weights. But for AI agents, learning can happen at three distinct layers: the model, the harness, and the context. Understanding the difference changes how you think about building systems that improve over time. The three main layers

share.google

Maina Wycliffe@mainawycliffe.dev · 4mo ago

Developer’s Guide to Building ADK Agents with Skills - Google Developers Blog share.google/dEGz2ZpaHuRW...

Developer’s Guide to Building ADK Agents with Skills- Google Developers Blog

Discover how the ADK SkillToolset uses progressive disclosure to build self-extending AI agents that load expertise on demand. Learn four patterns to reduce token costs and enable agents to dynamically generate their own skills using the agentskills.io specification.

share.google

Maina Wycliffe@mainawycliffe.dev · 4mo ago

One thing I've learnt building a production AI agent: persistent state isn't a nice-to-have — it's the foundation. Your agent sends a clarification message. The customer replies two days later. You need to resume exactly where you left off — not start over.

Maina Wycliffe@mainawycliffe.dev · 5mo ago

Migrating to Angular Signal Forms: Interop with Reactive Forms

Migrating to Angular Signal Forms: Interop with Reactive Forms - ANGULARarchitects

Dies ist Beitrag 3 von 3 der Serie “Signal Forms” Dynamic Forms: Building a Form Generator with Signal Forms Angular Signal Forms – Everything You Need to Know Migrating to Angular Signal Forms: Interop with Reactive Forms Signals Forms is the new Forms implementation in Angular. However, Reactive Forms will be supported for a long […]

angulararchitects.io