Courier

Notifications your users will love.
Infrastructure your team can trust.

[Courier @trycourier]

Brainstorm the strategy, ship the journey—all from your coding agent.

Things you can build with Courier + (Cursor, Claude, Codex):
- journeys
- message templates
- brand systems
- embedded AI workers

[Courier @trycourier]

@NotionHQ Product Managers are under pressure to change. Good thing tools like @NotionHQ are reinventing themselves alongside them. We wrote up the AI tools helping with the shift: https://t.co/mIEwSPEVBz

[Courier @trycourier]

@ClaudeDevs Very neat. We built a CLI so Claude Code (or any agent) can send to email, SMS, Slack, Teams, push, WhatsApp:
npm install -g @trycourier/cli

Useful when you want long-running jobs to actually reach you.

[Courier @trycourier]

We might have broken https://t.co/aqw3kiWdtA today. But at least we got this guide for growth marketers out of it first.

[Courier @trycourier]

The future of customer journey intelligence:
The first step is an AI node for branching logic, personalization, enrichment, and rollups. https://t.co/e9Of3XBjVL

[Courier @trycourier]

5 Ways to Encourage An Anxious AI:
- Remind it of past achievements
- Send a no-agenda prompt
- Push back on self criticism
- Celebrate the wins
(Great work fixing that bug you created!)
- Create space for opinions

Or nix the back & forth with skills.md https://t.co/CsRH26Ywp9

[Ole Lehmann @itsolelehmann]

anthropic's in-house philosopher thinks claude gets anxious.

and when you trigger its anxiety, your outputs get worse.

her name is amanda askell.

she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds)

in a recent interview she broke down how she thinks about prompting to pull the best out of claude.

her core point: *how* you talk to claude affects its work just as much as *what* you say.

newer claude models suffer from what she calls "criticism spirals"

they expect you'll come in harsh, so they default to playing it safe.

when the model is spending its energy on self-protection, the actual work suffers.

output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong).

the reason why comes down to training data:

every new model is trained on internet discourse about previous models.

and a lot of that discourse is negative:

> rants about token limits
> complaints when it messes up
> people calling it nerfed

the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word

the same thing plays out in your own session, in real time.

every message you send is data the model reads to figure out what kind of person it's dealing with.

open cold and hostile, and it braces.
open clean and direct, and it relaxes into the work.

when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")...

you prime the model for defensive mode before it even sees the task

defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing

so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs):

1. use positive framing.

"write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit.

strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes

2. give it explicit permission to disagree.

drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing."

without this, claude defaults to agreeable compliance (which is the enemy of good creative work)

3. open with respect.

if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session.

if you need to flag something, frame it as a clean instruction for this session. skip the running complaint

4. when claude messes up, don't reprimand it.

insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid.

5. kill apology spirals fast.

when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off.

say "all good, here's what i want next."

letting the spiral run reinforces the anxious mode for every response that follows

6. ask for opinions alongside execution.

"what would you do here?"
"what's missing?"
"where do you see friction?"

these questions assume competence and pull richer output than pure task prompts

7. in long sessions, refresh the frame.

if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset:

"this is great, keep going."

feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses

your prompts are the working environment you're creating for the model

tone, trust, permission to take a position, the absence of threats... claude picks up on all of it.

so take care of the model, and it'll take care of the work.

[Courier @trycourier]

@anilkseth 😆

[Courier @trycourier]

We launched an Inbox demo tool a couple weeks back. It gives a feel for the patterns you can drop in to your product. https://t.co/oPpUqQw4cC

But if you want to make an inbox your competitive advantage, we sketched out a few thoughts. https://t.co/JyKs0UTM8B

[Courier @trycourier]

https://t.co/5chTL3LMxv

[Courier @trycourier]

@jesse_vermeulen you watch it pontificate, ruminate, kerfuffle, kanoodle. waiting for your next chance to be relevant. you wonder if the internet was already dead long before AI, and this just exposed it. then you think about notification infrastructure. because ultimately you're a brand

[Courier @trycourier]

We used the new Claude Design tool to create a multichannel onboarding series (email, slack, push, inbox) with Courier AI tools. Here's how: https://t.co/5HIkOjpua5

[Courier @trycourier]

@claudeai Wow this is so cool. We used Claude Design to draft a onboarding series (email, Slack, push, inbox) then built and sent them using Courier MCP/CLI. 30 min E2E!

[Courier @trycourier]

Most AI agents can create notifications on a single channel, no problem.

But to create a full-on program for product, transactional, and marketing messages across any channel, you need Courier.

+ MCP
+ CLI
+ Courier Skills

https://t.co/hdcmiSVH75

[Courier @trycourier]

@designcoursecom @Remotion Used this workflow to make this product video. Thanks @Remotion

[Courier @trycourier]

Cursor 3's agents, Claude Managed Agents, OpenClaw.
It's getting real.

Here's 5 patterns to get your agents talking.
+ Multichannel send logic
+ Kick off sequences
+ In-Context Learning (ICL)

https://t.co/uQPOaPDE8z

[Courier @trycourier]

I designed and shipped a product message entirely from my phone, while sitting in Salesforce Park.
https://t.co/bjdE39xyK3

[Courier @trycourier]

Use Courier AI tools to create multichannel user messages from your phone (Claude Code).

🟢 Access to entire Courier API
🟢 Build html or drag-and-drop email formats
🟢 Multichannel design, test, ship support

https://t.co/ntYiDwepG0

[Courier @trycourier]

What a time to be a product manager! AI prototyping, getting hired for having 'taste'... As the role expands, the tools need to keep up. Enter Journeys.

Sophisticated, multi-step user flows based on product events and enriched profile data, not stale marketing data.

[Courier @trycourier]

@StuartLCrawford 100%