Rishi — Deep · Agentic

In short

Plans, executes, and then verifies its own work
Holds long multi-step runs together, end to end
The only model that accepts video as input and generates video
A 1M-token context
Slower and the most thorough — for when being wrong is expensive

Home×Find out why sign-ups drop…×

Find out why sign-ups dropped last week

Upfynworked for 16s

Planned: size the drop, find where, find whyRead 7 days of server logs, 1.2M linesFound the step where sign-ups stoppedVerified the cause against the release log

Daily sign-ups by platform

Release 5.2ThuFriSatSunMonTueWedThuFri

OTP texts failed for 71% of one carrier's users after Tuesday's release. Checked twice against the release log.

Ask anything...

Rishi Extra High

Rishiplans it, does it, checks it

0:15 / 0:19

Plans, executes, then checks

Rishi works across long multi-step runs: it plans the work, carries it out, and verifies the result before you see it. That is why it is slower, and why it costs the most per token.

Old field	New field	Rule	Settings
PaperSize	media.size	Name to ISO code	520
DPI	output.resolution	600 → "600x600"	520
ColourMode	colour.profile_ref	Name to profile ID	190
Duplex (Y/N)	finishing.sides	Y → two_sided_long	120
QueueName	workflow.queue_id	Look up in queue map	410
Timeout (sec)	workflow.timeout_ms	Seconds × 1,000	410

Batch	Setting type	In batch	First pass	Fixed on retry	Held
B1	Printer profiles	520	511	7	2
B2	Workflow templates	410	398	9	3
B3	Colour profiles	190	186	4	0
B4	Finishing presets	120	117	2	1
Total		1,240	1,212	22	6

Check	Method	Scope	Result	Status
Count parity	Script compare	1,240 settings	1,240 = 1,240	Pass
Schema validation	Schema v2 validator	1,240 settings	0 errors	Pass
Test print	Test page per device	38 devices	36 of 38 first time	Pass after fix
Workflow dry run	Sample job each	64 workflows	64 completed	Pass
Colour accuracy	Spectro, 12 swatches	190 profiles	188 within ΔE 2.0	Pass after fix
Rollback test	Restore snapshot	Chakan site	Restored in 11 min	Pass

Plan · Execute · Verify

Printer and workflow settings migration

1,240 settings moved from the legacy INI format to the new JSON schema

September 2026

1 / 10

Research you intend to act on

Reach for Rishi when a plausible wrong answer is the failure: research you mean to act on, an analysis someone will decide from, a change you are about to run. Let Bala and Yuva carry everything else.

Video in, video out

Rishi is the only one of the three that understands video and generates it.

Finish your research with something you can use

Compare options, collect evidence, and turn research into a useful brief with Upfyn. Keep the findings connected to the sources behind them.

Criterion	Weight	Caretrack	PatientLoop	Clinicore
Price	30%	4	3	5
Integrations	30%	4	5	3
Support	20%	4	4	2
Data residency	20%	5	3	5
Weighted score	100%	4.2	3.8	3.8
3-year cost		₹21.6 lakh	₹27.0 lakh	₹17.4 lakh

System	Caretrack	PatientLoop	Clinicore
Practice management	Native	Native	CSV import only
Lab results (LabBridge)	Native	Native	Planned, Q2 2027
SMS reminders	Built in	Built in	Paid add-on
Online booking widget	Built in	Built in	Built in
Accounts export	CSV and API	API	CSV
Open API	Full REST API	Full REST API	Read-only

Research brief

Choosing a patient CRM

Caretrack, PatientLoop and Clinicore compared for our five clinics

September 2026

1 / 10

Give your weekly report a repeatable starting point

Build a weekly report from your working files, refine it in chat, and schedule the preparation so you can spend more time reviewing the result.

Where it runs

Rishi is available wherever you use Upfyn: the desktop app and your phone. Your projects, tools and permissions stay with you when you switch between Bala, Yuva and Rishi.

How the three compare

	Bala	Yuva	Rishi
Best for	Everyday chat, drafting, high-volume text	Production chat, coding, vision + audio	Hard multi-step reasoning, research, media
Speed	Fastest	Fast	Deliberate
Depth	Direct — single pass	Considered — up to 2 stages	Agentic — most thorough
Modality	Text	Text + image + audio	Text + image + audio + video generation
Context	up to 1M	1M	1M
Plans	Every plan, including Free	Every plan, including Free	Every plan · usage charged in credits

Where it stops

Longer reasoning and media generation use more of your usage limit. Usage depends on the request, output length and tools used; there is no fixed number of runs per plan.

Availability

Every plan · usage charged in credits. Usage counts toward your plan’s limit; the plans and what each includes are on the pricing page.

See pricing Try it in Upfyn

Specifications

Speed: Deliberate
Depth: Agentic — most thorough
Modality: Text + image + audio + video generation
Context: 1M (1,000,000 tokens)
Plans: Every plan · usage charged in credits

The other two

Fast · EverydayBala Everyday chat, drafting, high-volume text Balanced · MultimodalYuva Production chat, coding, vision + audio

Meet Rishi