Ian Macartney
@ianmacartney.bsky.social
Friendly engineer at Convex.dev
Documentation for the Agent component is live 🎉
-> docs.convex.dev/agents
Odd coincidence that there's ~2300 lines of documentation & ~2300 lines of example code 🤔
...maybe more surprising there's fewer lines of React?
@convex-dev/agent
-> docs.convex.dev/agents
Odd coincidence that there's ~2300 lines of documentation & ~2300 lines of example code 🤔
...maybe more surprising there's fewer lines of React?
@convex-dev/agent
July 22, 2025 at 5:31 AM
Documentation for the Agent component is live 🎉
-> docs.convex.dev/agents
Odd coincidence that there's ~2300 lines of documentation & ~2300 lines of example code 🤔
...maybe more surprising there's fewer lines of React?
@convex-dev/agent
-> docs.convex.dev/agents
Odd coincidence that there's ~2300 lines of documentation & ~2300 lines of example code 🤔
...maybe more surprising there's fewer lines of React?
@convex-dev/agent
Rate limiting LLM chat per-user with `useRateLimit`
const { status } = useRateLimit(api.rl.getRateLimit)
Full code in 🧵
Algorithms:
Sending messages: fixed window
Token usage: token bucket
courtesy of
@convex-dev/rate-limiter + @convex-dev/agent
(components)
const { status } = useRateLimit(api.rl.getRateLimit)
Full code in 🧵
Algorithms:
Sending messages: fixed window
Token usage: token bucket
courtesy of
@convex-dev/rate-limiter + @convex-dev/agent
(components)
June 17, 2025 at 8:44 PM
Rate limiting LLM chat per-user with `useRateLimit`
const { status } = useRateLimit(api.rl.getRateLimit)
Full code in 🧵
Algorithms:
Sending messages: fixed window
Token usage: token bucket
courtesy of
@convex-dev/rate-limiter + @convex-dev/agent
(components)
const { status } = useRateLimit(api.rl.getRateLimit)
Full code in 🧵
Algorithms:
Sending messages: fixed window
Token usage: token bucket
courtesy of
@convex-dev/rate-limiter + @convex-dev/agent
(components)
Recent talk on agents & agentic workflows, as well as my Convex Agent Component. Takes:
• Agentic := prompting + routing
• Prompting is input -> LLM -> output
• Routing has code at every boundary
(...even if an LLM "decides" what to do next)
Full 📺🔗->🧵
• Agentic := prompting + routing
• Prompting is input -> LLM -> output
• Routing has code at every boundary
(...even if an LLM "decides" what to do next)
Full 📺🔗->🧵
June 9, 2025 at 11:51 PM
Recent talk on agents & agentic workflows, as well as my Convex Agent Component. Takes:
• Agentic := prompting + routing
• Prompting is input -> LLM -> output
• Routing has code at every boundary
(...even if an LLM "decides" what to do next)
Full 📺🔗->🧵
• Agentic := prompting + routing
• Prompting is input -> LLM -> output
• Routing has code at every boundary
(...even if an LLM "decides" what to do next)
Full 📺🔗->🧵
Streaming LLM text using websockets + client smoothing - no HTTP necessary!
Agent v0.2.1 is out! Repo & release notes in 🧵
- Streaming text react hook + server fns
- Client-side smoothing hook
- Optimistic update helpers
Agent v0.2.1 is out! Repo & release notes in 🧵
- Streaming text react hook + server fns
- Client-side smoothing hook
- Optimistic update helpers
May 31, 2025 at 8:16 AM
Streaming LLM text using websockets + client smoothing - no HTTP necessary!
Agent v0.2.1 is out! Repo & release notes in 🧵
- Streaming text react hook + server fns
- Client-side smoothing hook
- Optimistic update helpers
Agent v0.2.1 is out! Repo & release notes in 🧵
- Streaming text react hook + server fns
- Client-side smoothing hook
- Optimistic update helpers
Agent Playground for @convex-dev/agent is live!
Investigate threads, messages, tool calls
Dial in context params
Iterate on prompting, etc.
For the @convex-dev/agent component.
Links in 🧵
Investigate threads, messages, tool calls
Dial in context params
Iterate on prompting, etc.
For the @convex-dev/agent component.
Links in 🧵
May 22, 2025 at 11:52 PM
Agent Playground for @convex-dev/agent is live!
Investigate threads, messages, tool calls
Dial in context params
Iterate on prompting, etc.
For the @convex-dev/agent component.
Links in 🧵
Investigate threads, messages, tool calls
Dial in context params
Iterate on prompting, etc.
For the @convex-dev/agent component.
Links in 🧵
I do RAG via hybrid text/vector search using reciprocal rank fusion (the one-weird-trick of hybrid search imo) for my new Agent framework/component.
It's open source and the code is remarkably simple, if you're looking for an example for yourself.
It's open source and the code is remarkably simple, if you're looking for an example for yourself.
![let textSearchMessages: Doc<"messages">[] | undefined;
if (args.text) {
textSearchMessages = await ctx.runQuery(api.messages.textSearch, {
userId: args.userId,
threadId: args.threadId,
text: args.text,
limit,
});
}
if (args.vector) {
const dimension = args.vector.length as VectorDimension;
if (!VectorDimensions.includes(dimension)) {
throw new Error(`Unsupported vector dimension: ${dimension}`);
}
const vectors = (
await searchVectors(ctx, args.vector, {
dimension,
model: args.vectorModel ?? "unknown",
table: "messages",
userId: args.userId,
threadId: args.threadId,
limit,
})
).filter((v) => v._score > (args.vectorScoreThreshold ?? 0));
// Reciprocal rank fusion
const k = 10;
const textEmbeddingIds = textSearchMessages?.map((m) => m.embeddingId);
const vectorScores = vectors
.map((v, i) => ({
id: v._id,
score:
1 / (i + k) +
1 / ((textEmbeddingIds?.indexOf(v._id) ?? Infinity) + k),
}))
.sort((a, b) => b.score - a.score);
const vectorIds = vectorScores.slice(0, limit).map((v) => v.id);
const messages: Doc<"messages">[] = await ctx.runQuery(
internal.messages._fetchVectorMessages,
{
userId: args.userId,
threadId: args.threadId,
vectorIds,
textSearchMessages: textSearchMessages?.filter(
(m) => !vectorIds.includes(m.embeddingId!)
),
messageRange: args.messageRange ?? DEFAULT_MESSAGE_RANGE,
parentMessageId: args.parentMessageId,
limit,
}
);
return messages;
}
return textSearchMessages?.flat() ?? [];](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:bjnfjbytpwb2w7xlge775hwd/bafkreigvscvz7oymepul3uakdbx5y73hnun4lw2eifhp6coye6m3oko4iy@jpeg)
April 10, 2025 at 12:59 AM
I do RAG via hybrid text/vector search using reciprocal rank fusion (the one-weird-trick of hybrid search imo) for my new Agent framework/component.
It's open source and the code is remarkably simple, if you're looking for an example for yourself.
It's open source and the code is remarkably simple, if you're looking for an example for yourself.
Welp not all experiments work out, but what will outlive all products is the insights you glean along the way.
I reimplemented Mastra workflows in Convex last week and I regret it. Article in 🧵
I reimplemented Mastra workflows in Convex last week and I regret it. Article in 🧵
March 31, 2025 at 8:35 PM
Welp not all experiments work out, but what will outlive all products is the insights you glean along the way.
I reimplemented Mastra workflows in Convex last week and I regret it. Article in 🧵
I reimplemented Mastra workflows in Convex last week and I regret it. Article in 🧵
I made some cartoons today for an article I'm writing.
This one is me when I'm too deep in a project that's gone off the rails, complete with alt text.
Should I ship it or make a "better" version to make it "more professional"?
This one is me when I'm too deep in a project that's gone off the rails, complete with alt text.
Should I ship it or make a "better" version to make it "more professional"?
March 28, 2025 at 3:04 AM
I made some cartoons today for an article I'm writing.
This one is me when I'm too deep in a project that's gone off the rails, complete with alt text.
Should I ship it or make a "better" version to make it "more professional"?
This one is me when I'm too deep in a project that's gone off the rails, complete with alt text.
Should I ship it or make a "better" version to make it "more professional"?
Programmers know why this sorting is busted the way it is.
Maybe they should also know better :P
Maybe they should also know better :P
March 27, 2025 at 8:47 PM
Programmers know why this sorting is busted the way it is.
Maybe they should also know better :P
Maybe they should also know better :P
Thoughts on about safety & reliability in the age of agentic flows and durable workflows:
Details in 🧵, but tl;dr:
1️⃣ Isolate unreliable steps to safely retry
2️⃣ Model LLMs as ~idempotent & ~deterministic
3️⃣ Run asynchronously, subscribe to results
Bonus: I made a thing
Details in 🧵, but tl;dr:
1️⃣ Isolate unreliable steps to safely retry
2️⃣ Model LLMs as ~idempotent & ~deterministic
3️⃣ Run asynchronously, subscribe to results
Bonus: I made a thing
March 25, 2025 at 11:44 PM
Thoughts on about safety & reliability in the age of agentic flows and durable workflows:
Details in 🧵, but tl;dr:
1️⃣ Isolate unreliable steps to safely retry
2️⃣ Model LLMs as ~idempotent & ~deterministic
3️⃣ Run asynchronously, subscribe to results
Bonus: I made a thing
Details in 🧵, but tl;dr:
1️⃣ Isolate unreliable steps to safely retry
2️⃣ Model LLMs as ~idempotent & ~deterministic
3️⃣ Run asynchronously, subscribe to results
Bonus: I made a thing
Made this architecture diagram yesterday, implementing it today. Any guesses on what it is? Wish me luck!
March 22, 2025 at 12:11 AM
Made this architecture diagram yesterday, implementing it today. Any guesses on what it is? Wish me luck!
Tiago asked about integrating reactflow.dev
with @convex.dev so I made a demo last night.
- realtime syncing flow chart
- authorize reads and writes
- validation of custom data payloads
- optimistic updates for UX 🧑🍳💋
I'm proud of it, and thanks Tiago for the help!
github.com/ianmacartney...
with @convex.dev so I made a demo last night.
- realtime syncing flow chart
- authorize reads and writes
- validation of custom data payloads
- optimistic updates for UX 🧑🍳💋
I'm proud of it, and thanks Tiago for the help!
github.com/ianmacartney...
March 11, 2025 at 8:21 PM
Tiago asked about integrating reactflow.dev
with @convex.dev so I made a demo last night.
- realtime syncing flow chart
- authorize reads and writes
- validation of custom data payloads
- optimistic updates for UX 🧑🍳💋
I'm proud of it, and thanks Tiago for the help!
github.com/ianmacartney...
with @convex.dev so I made a demo last night.
- realtime syncing flow chart
- authorize reads and writes
- validation of custom data payloads
- optimistic updates for UX 🧑🍳💋
I'm proud of it, and thanks Tiago for the help!
github.com/ianmacartney...
The Telepathy Tapes podcast is adding to the pile of worldview-changing things to grapple with.
What deserves my attention?
What deserves my attention?
February 20, 2025 at 1:45 AM
The Telepathy Tapes podcast is adding to the pile of worldview-changing things to grapple with.
What deserves my attention?
What deserves my attention?
Local file sharing app (Open Source)
Drag your files onto the site
Drag them off on another computer
git clone github.com/mikecann/our...
cd ourfiles/
docker compose up
open localhost:5173
by
@mikeysee
video in 🧵
Drag your files onto the site
Drag them off on another computer
git clone github.com/mikecann/our...
cd ourfiles/
docker compose up
open localhost:5173
by
@mikeysee
video in 🧵
February 14, 2025 at 8:26 PM
Local file sharing app (Open Source)
Drag your files onto the site
Drag them off on another computer
git clone github.com/mikecann/our...
cd ourfiles/
docker compose up
open localhost:5173
by
@mikeysee
video in 🧵
Drag your files onto the site
Drag them off on another computer
git clone github.com/mikecann/our...
cd ourfiles/
docker compose up
open localhost:5173
by
@mikeysee
video in 🧵
Self-hosting Convex just got way easier,
including running the dashboard.
npx degit get-convex/convex-backend/self-hosted/fly fly && cd fly/backend && fly launch
Dockerfiles, images, binaries @flydotio and more.
Check it out 🧵
including running the dashboard.
npx degit get-convex/convex-backend/self-hosted/fly fly && cd fly/backend && fly launch
Dockerfiles, images, binaries @flydotio and more.
Check it out 🧵
February 13, 2025 at 3:55 PM
Self-hosting Convex just got way easier,
including running the dashboard.
npx degit get-convex/convex-backend/self-hosted/fly fly && cd fly/backend && fly launch
Dockerfiles, images, binaries @flydotio and more.
Check it out 🧵
including running the dashboard.
npx degit get-convex/convex-backend/self-hosted/fly fly && cd fly/backend && fly launch
Dockerfiles, images, binaries @flydotio and more.
Check it out 🧵
Another feature of the BlockNote/Tiptap sync component that might interest folks:
Server-side document editing, w/o clobbering user changes
You can access & transform a document, but the really cool thing is that you provide a callback to rebase your transform on the latest version.
Server-side document editing, w/o clobbering user changes
You can access & transform a document, but the really cool thing is that you provide a callback to rebase your transform on the latest version.
January 28, 2025 at 10:32 PM
Another feature of the BlockNote/Tiptap sync component that might interest folks:
Server-side document editing, w/o clobbering user changes
You can access & transform a document, but the really cool thing is that you provide a callback to rebase your transform on the latest version.
Server-side document editing, w/o clobbering user changes
You can access & transform a document, but the really cool thing is that you provide a callback to rebase your transform on the latest version.
Some improvements to the open-source collaborative editor sync component landed this week:
📝 Now supports syncing *BlockNote* & @tiptap.dev
🦾 Server-side editing of documents is now easier & documented, for those of you using AI thingies
📝 Now supports syncing *BlockNote* & @tiptap.dev
🦾 Server-side editing of documents is now easier & documented, for those of you using AI thingies
January 23, 2025 at 10:11 PM
Some improvements to the open-source collaborative editor sync component landed this week:
📝 Now supports syncing *BlockNote* & @tiptap.dev
🦾 Server-side editing of documents is now easier & documented, for those of you using AI thingies
📝 Now supports syncing *BlockNote* & @tiptap.dev
🦾 Server-side editing of documents is now easier & documented, for those of you using AI thingies