See how fast feels
Joined January 2014
- Tweets 14,116
- Following 3,029
- Followers 44,004
- Likes 8,458
6,237 Photos and videos
"A little memory and access to actual data." That's all @cassidoo wanted for her agent.
What she got instead: retrieval, sync pipelines, permissions, caching, and a full taxonomy of what agents should remember, forget, and never touch.
Her piece in TLDR is one of the most honest (and funniest) accounts we've seen of why agent context is real infrastructure, and exactly why Redis Iris exists.
1
1
2
1,031
Worth the read: tldr.tech/blog/context-layer…
1
941
Redis retweeted
Jun 12
Most AI agents don't fail because they're dumb.
They fail because they can't find the right data.
The model is smart. But the data it needs is spread out. Some sits in your database. Some in a ticket system. Some in an old doc no one has opened in months.
So the agent guesses. And you get a bad answer.
If you've built an app like this, you know the pain. The data lives in five places. None of it talks to each other. And now we're asking AI to make sense of all of it, live.
Here's what I keep coming back to: this is a tooling problem, not a brains problem. If we want AI to work at scale, we need better plumbing under it.
That's why Redis Iris caught my eye. It's a "context engine". Think of it as a layer that sits between your agent and your data. Its one job is to feed the agent the right context, fast.
A few things it does:
- Pulls live data from your systems, so nothing goes stale
- Gives the agent a clean path to your data, so it stops guessing
- Remembers past chats, so it doesn't start from zero each time
- Caches repeat answers to save time and tokens
What I like most: it's built on Redis. The same tool a lot of us already trust for caching. So it's not one more strange thing to learn.
We're still early in all of this. But better tools like this are how AI agents go from "cool demo" to "I trust it in production".
Curious how it works? Take a look here: fandf.co/3Qan56b
Thanks to @Redisinc for sponsoring this post.
5
4
37
2,516
Big congrats to Jin Choi, Vinay Bhagavath, Vijay Sithambaram, and Christin Philip — the winners of Best Use of Redis at WeaveHacks 4 this weekend!
Their project, Rezn, didn't just use Redis as infrastructure. It made Redis part of the creative loop.
rezn-ai generates music candidates, lets a producer approve, reject, or refine them, then uses that feedback to make the next generation smarter. The more a producer interacts, the more the system learns their taste.
1
3
1,030
This is exactly where Redis Iris shines, giving agents memory that outlasts a single prompt. This is exactly where Redis Iris shines, giving agents memory that outlasts a single prompt. More about Rezn:
💻 Repo: github.com/gorajing/rezn-ai
🎥 Demo: youtube.com/watch?v=G7IgUwm7…
229
Redis retweeted
Jun 8
what a blast at WeaveHacks this weekend! thanks for hosting @wandb🎉🎉
& congrats to EmailSignal for winning best use of @CopilotKit🪁!
saw so many dope projects, ranging from AG-UI in VR to cardiology. it’s exciting to see what people can hack together in <48 hours
always great to co-sponsor alongside our friends @Redisinc, @OpenAI, & @cursor_ai. huge shoutout to Alex & Anna for running the event
Jun 6
Biggest turnout we've had at @wandb hackathon ever (Sorry for folks who couldn't get in) The energy is insane!
Looking forward to incredible hacks over the weekend, hackers are pumped!
Thank you sponsors @Redisinc @OpenAIDevs @cursor_ai and @CopilotKit
4
4
56
8,213
Redis retweeted
Jun 6
Biggest turnout we've had at @wandb hackathon ever (Sorry for folks who couldn't get in) The energy is insane!
Looking forward to incredible hacks over the weekend, hackers are pumped!
Thank you sponsors @Redisinc @OpenAIDevs @cursor_ai and @CopilotKit
2
7
36
11,114
Building agents? Check out this hour-long masterclass by @SonnySangha on breaking through the context bottleneck so you can build agents that actually work. Watch here: youtube.com/watch?v=PoMEGxNL…
1
2
7
1,849
Redis 8.8 is here — free to download for anyone on Redis Open Source.
New data structure, a built-in rate limiter, faster streams, and throughput gains across the board. Read all about it here: redis.io/blog/announcing-red… 🧵
1
5
20
1,723
Plus end-to-end throughput improvements across strings, hashes, streams, sorted sets, bitmaps, and more. Download Redis 8.8 here: redis.io/downloads/
182