---
title: "Why Can't I Talk to My Tools, and Why Don't They Know What to Do?"
description: "On the friction of retrieving information during conversations and the potential of contextual AI assistance"
type: note
pubDate: 2022-09-22T00:00:00.000Z
topics: ["thought", "ai", "ux", "communication"]
canonicalUrl: "https://actuallymaybe.com/blog/quick-thought/"
---
> On the friction of retrieving information during conversations and the potential of contextual AI assistance

Often when writing a message to someone, I need to recall some piece of information or idea. Maybe it's a funny meme or an interesting stat. Regardless, you typically have to leave the messaging application you're in and navigate either to some central store or the source application (usually it's some errant bookmark) to remember what the hell you were searching for again. Maybe you switch back to the messaging application to remind yourself, then carry out the search. You then need to download that information or copy it, paste it into the messaging application, and send.

What I've massively glossed over is all the friction from speed and all the distractions along the way as you open up the browser and see the tab you're on about the potted history of some obscure bureaucrat, and proceed to resist the temptation to get distracted. All the while, you vaguely paw at the keyboard in a futile attempt to remember what you want.

Why can't the experience be as simple as messaging your creative store and getting a nice contextual response? You could even let it peek at what you were just chatting about, and it could draw on that connective and contextual relevance. It could send directly back to you, within the messaging application, the glorious statistic you need on horse deployments in Finland in 1955.[^1]

Allowing you to continue your chat undistracted.

[^1]: Finland reached peak horse in 1955.

## Further reading
- [Notes on Visual Interfaces, AI Tooling, Fast LLMs and Decision Models](https://actuallymaybe.com/blog/notes-visual-interfaces-ai-tooling-fast-llms-decision-models/) — Why agentic work is stuck in text, and what canvases, fast models, branching version graphs, and decision models might add.
- [Emerging Field of Epistemic Engineering or Stochastic Management](https://actuallymaybe.com/blog/emerging-field-epistemic-engineering/) — Practices around context, uncertainty, and evals are hardening into a discipline, with belief states at its centre: probabilistic, grounded views of a work process.
- [The Different Problems of Searching Global and Local Context](https://actuallymaybe.com/blog/global-vs-local-context-search/) — Exploring why global-context search is easier than local-context search, and what tools built with local context in mind might look like
- [The AI Tool That I Wish Existed](https://actuallymaybe.com/blog/ai-tool-wish-existed/) — Envisioning an AI-first productivity tool that anticipates, connects, and surfaces ideas rather than requiring explicit organisation