The same holds for answers on your own website. Companion answers from the pages and documents you select, cites each claim, and replaces unsupported output before a visitor sees it. companion.switchcasestudios.com
FACT: Better AI shopping experiences start with better context.
🏷️ Product data
⭐ Reviews & ratings
📄 Content
⚙️ Business rules
📈 Relevance signals
🛍️ Shopper context
Algolia Agent Studio brings it all together so AI can retrieve the right products and answers for every shopmes together: bit.ly/4wCGGvc
0
0
1
3
Not every file deserves a permanent address. SwitchCase Files gives it a link and a QR code for 1, 6 or 24 hours, no account needed, then lets it go. files.switchcasestudios.com
0
0
1
6
SwitchCase Studios retweeted
fun fact. I use this on the SwitchCase website. Eat your own dog food.
An assistant that sounds sure and is wrong costs more than one that says it doesn't know. Companion checks each answer against the passages it retrieved, cites its sources, and replaces unsupported output before a visitor sees it. companion.switchcasestudios.com
0
1
0
7
Every summit ends up with the registration link, the agenda and the session video spread across three posts. A SimpURL page keeps them together behind one link. Free includes a profile page with 6 links or video players. simpurl.click
How can AI shape a better future for education? Hear from featured speakers driving change at the Canadian EdTech Leadership AI Summit, October 28–29 at UTM. Connect, learn and be inspired. Register now! #mindshare #EdTech #AI #UTM #EdTechSummit
0
0
0
5
A survey result is only useful if you know which question produced it. SwitchForms keeps each published version as read-only history, so last month's answers stay readable after this month's edits. 14 days of Scale on your first workspace, no card. switchforms.app
0
0
0
7
Tracing shows what an agent did. For customer-facing answers we also want to see what it could not support. Companion checks answers against the passages it retrieved, replaces unsupported output before a visitor sees it, and queues knowledge gaps for review. companion.switchcasestudios.com
Trace and evaluate Cursor agents with @langfuse.
Inspect model calls, tool executions, and token usage. Find expensive turns and test instruction changes. ClickHouse powers the analytics behind Langfuse.
Read the guide: clickhouse.com/blog/cursor-ag…
0
0
0
5
A spreadsheet of short links is not a campaign system. It is a future archaeology project. SimpURL keeps custom links, branded QR codes and campaign analytics in one place, with tags and expiry attached. simpurl.click
0
0
1
6
Release calls juggle a registration link, a changelog and a replay. A SimpURL page keeps them together on one link, with blocks for links and video. Free includes a profile page, and paid plans go to 10 pages. simpurl.click
Just a few hours until the ClickHouse 26.10 release call ⏰
Alexey walks through the release live at 4pm UK / 8am PT, with demos and Q&A: c.house/2610ReleaseCall
0
0
1
5
An assistant that sounds sure and is wrong costs more than one that says it doesn't know. Companion checks each answer against the passages it retrieved, cites its sources, and replaces unsupported output before a visitor sees it. companion.switchcasestudios.com
0
0
1
10
Agent analytics is where the real product work starts. On the Companion side, the view we find most useful is the list of visitor questions the knowledge base can't answer yet. It tells owners exactly what to write next.
🚀 Day 3/5 of telli Launch Week
Introducing Analytics: track your agents' performance and identify areas for improvement.
Start with a template, build your own dashboard, or ask Charlie to create one for you.
Then share your insights across the company with interactive reports.
0
0
0
3
Agent analytics is where the real product work starts. On the Companion side, the view we find most useful is the list of visitor questions the knowledge base can't answer yet. It tells owners exactly what to write next.
🚀 Day 3/5 of telli Launch Week
Introducing Analytics: track your agents' performance and identify areas for improvement.
Start with a template, build your own dashboard, or ask Charlie to create one for you.
Then share your insights across the company with interactive reports.
0
0
0
4
Hours of public meetings that nobody watches is a searchable knowledge base waiting to happen. Same idea behind Companion on business sites: answers grounded in the real source, not guesses. Great use of diarization.
City councils decide on real estate development and rezoning in meetings almost nobody watches.
Today @myhamletinc & @subes01 launched 10,000+ profiles, available for residents and journalists, powered by AssemblyAI Universal-3.5 Pro and speaker diarization.
Read the full storwTO
0
0
0
4
Keeping the pink while changing the type around it is the hard part of any rebrand. We refreshed SwitchCase last week and learned the same thing: change what you need to, keep what people already recognize.
What happens between the nodes?
That's the idea behind the new n8n logo, unveiled at In The Loop, our first-ever conference. New typeface, same iconic pink. Same community of builders.
#n8n #InTheLoop2026 #branding
0
0
0
12
Putting the agent inside the meeting is the hard part done. The next question is what it is allowed to say. With Companion we ground every answer in the business's own knowledge base, so when it answers out loud, it answers from evidence, not guesswork.
Want an AI voice agent that joins your Zoom, Meet or Teams call and answers questions out loud?
@recallai just published the full build. AssemblyAI's Voice Agent API listens, thinks and speaks. Recall.ai's Output Media puts it in the meeting.
recall.ai/blog/how-to-bu…
0
0
0
10
Declaring the allowed labels up front is what makes triage trustworthy. We take the same approach with intake in SwitchForms: fix the categories at the form, and every submission lands where it should without cleanup later.
The changelog example sorts a support ticket into bug, feature, or question. You hand Jev the ticket text as state, declare the three labels you'll accept, and the answer comes back as one of them. There's nothing to parse on your end.
netlify.com/changelog/type…
0
0
0
10
SwitchCase Studios retweeted
Dot needs to be faster at responding and be more proactive, it also needs a secure credential manager like Muse has and Grok Bot if it’s going to compete, Tibo @thsottiaux
Muse literally says “hey, I can help with this…” for non technical users that’s a massive W.
Muse literally says “hey, I can help with this…” for non technical users that’s a massive W.
0
1
0
44
Live queries inside Postgres is a big deal for anyone building dashboards. Most product metrics go stale between refreshes, and that gap is where teams start doubting the numbers. It's the problem we keep coming back to with SwitchLens.
New in Neon this week:
- Neon Realtime is in public beta: turn any SQL query into a live query, right inside Postgres
- 11 new models for AI Gateway, including Claude Sonnet 5.5, Claude Haiku 5.5, GPT-6 Sol, GPT-6 Luna, and more
- Managed Better Auth now runs Better Auth 1.7
0
0
1
10
Frontier models running on a desk changes who gets to prototype. For Companion, we care less about where inference runs and more about what it is allowed to say: answers grounded in your own knowledge base, with visitor memory treated as context, not evidence.
0
0
0
6
SwitchCase Studios retweeted
The “ideas” section on Muse is something that Dots or Grok Bot needs to adopt. It’s incredibly useful to take conversations and have the AI make recommendations on how it can help and within a click, setup an agentic workflow to execute. Killer idea on Metas behalf.
2
1
0
39
Teams of agents only work when they share context across sessions. That is the gap we built Companion for: verified cross-device memory so the workforce remembers what already happened.
Your agents should be a workforce, not a factory.
Nick Wong from @cognition came to Navigate 2026 and walked through how to actually create effective teams of agents.
0
0
1
10