The Standard of Proof, Delivered
Touchstone runs quality as one closed loop, from requirement to test to evidence. Agents do the work, your team approves it, and every artefact can prove where it came from.
The Standard of Proof, Delivered
Touchstone runs quality as one closed loop, from requirement to test to evidence. Agents do the work, your team approves it, and every artefact can prove where it came from.
The Standard of Proof, Delivered
Touchstone runs quality as one closed loop, from requirement to test to evidence. Agents do the work, your team approves it, and every artefact can prove where it came from.
Trusted where releases carry consequences
Trusted where releases carry consequences
Trusted where releases carry consequences
Trusted where releases carry consequences
A Generator Gives You Tests, a Loop Gives You a System
Any AI tool can write test steps in seconds. What's left behind is a pile of scripts with no reason, no owner and no plan for when the app changes.
Generated tests carry no context
They reflect the prompt, not the requirement. Nobody knows which business rule they prove, or if it still applies.
Maintenance arrives as a separate bill
Generation solves the first hour. Tracing and repairing every change after that stays manual.
No chain of evidence
With no link from requirement to test to result, a suite is just a collection, not a system that can account for itself.
A Generator Gives You Tests, a Loop Gives You a System
Any AI tool can write test steps in seconds. What's left behind is a pile of scripts with no reason, no owner and no plan for when the app changes.
Generated tests carry no context
They reflect the prompt, not the requirement. Nobody knows which business rule they prove, or if it still applies.
Maintenance arrives as a separate bill
Generation solves the first hour. Tracing and repairing every change after that stays manual.
No chain of evidence
With no link from requirement to test to result, a suite is just a collection, not a system that can account for itself.
A Generator Gives You Tests, a Loop Gives You a System
Any AI tool can write test steps in seconds. What's left behind is a pile of scripts with no reason, no owner and no plan for when the app changes.
Generated tests carry no context
They reflect the prompt, not the requirement. Nobody knows which business rule they prove, or if it still applies.
Maintenance arrives as a separate bill
Generation solves the first hour. Tracing and repairing every change after that stays manual.
No chain of evidence
With no link from requirement to test to result, a suite is just a collection, not a system that can account for itself.
Three Agents Orchestrate, Specialised Agents Do the Work, Your Team Governs
Touchstone's agents take work from requirement to journey to runnable test, each grounded in your sources and standards. Your team reviews, edits and approves at every stage, so nothing moves forward without a person signing it off.
The Analyst understands your documents
Turns tickets and specs into testable requirements, each citing its source.
The Architect shapes the journey
Builds requirements into full journeys, reusing the checkpoints, data and environments you already have.
The Autopilot builds
Runs the journey in a real browser with its reasoning visible, so every gap comes with an explanation.
The Knowledge Base grounds every generation
Your specs, designs and policies in one place. Every output cites what it used.
Agent Directives apply your conventions
Naming, templates and domain rules in plain language, applied to everything the agents produce.
A deterministic engine executes
30+ specialised agents drive the workflows. Approved journeys run on an engine that behaves the same way every time.
Three Agents Orchestrate, Specialised Agents Do the Work, Your Team Governs
Touchstone's agents take work from requirement to journey to runnable test, each grounded in your sources and standards. Your team reviews, edits and approves at every stage, so nothing moves forward without a person signing it off.
The Analyst understands your documents
Turns tickets and specs into testable requirements, each citing its source.
The Architect shapes the journey
Builds requirements into full journeys, reusing the checkpoints, data and environments you already have.
The Autopilot builds
Runs the journey in a real browser with its reasoning visible, so every gap comes with an explanation.
The Knowledge Base grounds every generation
Your specs, designs and policies in one place. Every output cites what it used.
Agent Directives apply your conventions
Naming, templates and domain rules in plain language, applied to everything the agents produce.
A deterministic engine executes
30+ specialised agents drive the workflows. Approved journeys run on an engine that behaves the same way every time.
Three Agents Orchestrate, Specialised Agents Do the Work, Your Team Governs
Touchstone's agents take work from requirement to journey to runnable test, each grounded in your sources and standards. Your team reviews, edits and approves at every stage, so nothing moves forward without a person signing it off.
The Analyst understands your documents
Turns tickets and specs into testable requirements, each citing its source.
The Architect shapes the journey
Builds requirements into full journeys, reusing the checkpoints, data and environments you already have.
The Autopilot builds
Runs the journey in a real browser with its reasoning visible, so every gap comes with an explanation.
The Knowledge Base grounds every generation
Your specs, designs and policies in one place. Every output cites what it used.
Agent Directives apply your conventions
Naming, templates and domain rules in plain language, applied to everything the agents produce.
A deterministic engine executes
30+ specialised agents drive the workflows. Approved journeys run on an engine that behaves the same way every time.
Keep Test Coverage Aligned with Application Change
When an application changes, Touchstone preserves the traceability between the updated source and the requirements derived. It compares document versions, filters out cosmetic edits and surfaces only changes that may affect test coverage. Only affected requirements are flagged for review. Each receives a Mandatory, Optional or No change verdict, after which approved requirement changes flag the journeys linked to them. Coverage is not rewritten automatically, giving teams traceability across every change and control over what moves forward.
Keep Test Coverage Aligned with Application Change
When an application changes, Touchstone preserves the traceability between the updated source and the requirements derived. It compares document versions, filters out cosmetic edits and surfaces only changes that may affect test coverage. Only affected requirements are flagged for review. Each receives a Mandatory, Optional or No change verdict, after which approved requirement changes flag the journeys linked to them. Coverage is not rewritten automatically, giving teams traceability across every change and control over what moves forward.
Keep Test Coverage Aligned with Application Change
When an application changes, Touchstone preserves the traceability between the updated source and the requirements derived. It compares document versions, filters out cosmetic edits and surfaces only changes that may affect test coverage. Only affected requirements are flagged for review. Each receives a Mandatory, Optional or No change verdict, after which approved requirement changes flag the journeys linked to them. Coverage is not rewritten automatically, giving teams traceability across every change and control over what moves forward.
Keep Test Coverage Aligned with Application Change
When an application changes, Touchstone preserves the traceability between the updated source and the requirements derived. It compares document versions, filters out cosmetic edits and surfaces only changes that may affect test coverage. Only affected requirements are flagged for review. Each receives a Mandatory, Optional or No change verdict, after which approved requirement changes flag the journeys linked to them. Coverage is not rewritten automatically, giving teams traceability across every change and control over what moves forward.
What Our Beta Customers Say About Touchstone
"It's something a human would do, not a tool."
Late deliveries made in-sprint automation a struggle. Now we upload requirements early and have everything ready when the feature lands.
- Test automation engineer, Global insurer
"Almost 15 out of 10."
Our material isn't well organised. It makes sense to us, but I'm impressed by how Touchstone made sense of all of it and fit it into this template. Very Impressive.
- QA and delivery lead, Global IT services provider
"I wouldn't say it's left any big gaping holes."
Comparing the PDF I provided with what came out, I think it's really good. It's exciting to see it take a PDF without much information.
- Automation engineer, Software company
"It's almost scary how accurate it is."
I wrote just a couple of sentences and Touchstone knew the whole application. Honestly, I was pretty impressed with how quickly it got there.
- Tester, IP and research data company
"It won't just assume success and carry on blithely."
I really approve of this. You've clearly built in the right guardrails, so it checks its results instead of assuming everything worked.
- Testing lead, Global engineering consultancy
"It would actually help my testers not over-test."
It's de-scoped the declines. It's not testing the whole decline flow, only that you can change a decision, which is exactly right. Really accurate.
- Test lead, Financial services group
What Our Beta Customers Say About Touchstone
"It's almost scary how accurate it is."
I wrote just a couple of sentences and Touchstone knew the whole application. Honestly, I was pretty impressed with how quickly it got there.
- Tester, IP and research data company
"I wouldn't say it's left any big gaping holes."
Comparing the PDF I provided with what came out, I think it's really good. It's exciting to see it take a PDF without much information.
- Automation engineer, Software company
"Almost 15 out of 10."
Our material isn't well organised. It makes sense to us, but I'm impressed by how Touchstone made sense of all of it and fit it into this template. Very Impressive.
- QA and delivery lead, Global IT services provider
"It's something a human would do, not a tool."
Late deliveries made in-sprint automation a struggle. Now we upload requirements early and have everything ready when the feature lands.
- Test automation engineer, Global insurer
"It won't just assume success and carry on blithely."
I really approve of this. You've clearly built in the right guardrails, so it checks its results instead of assuming everything worked.
- Testing lead, Global engineering consultancy
"It would actually help my testers not over-test."
It's de-scoped the declines. It's not testing the whole decline flow, only that you can change a decision, which is exactly right. Really accurate.
- Test lead, Financial services group
What Our Beta Customers Say About Touchstone
"It's something a human would do, not a tool."
Late deliveries made in-sprint automation a struggle. Now we upload requirements early and have everything ready when the feature lands.
- Test automation engineer, Global insurer
"Almost 15 out of 10."
Our material isn't well organised. It makes sense to us, but I'm impressed by how Touchstone made sense of all of it and fit it into this template. Very Impressive.
- QA and delivery lead, Global IT services provider
"I wouldn't say it's left any big gaping holes."
Comparing the PDF I provided with what came out, I think it's really good. It's exciting to see it take a PDF without much information.
- Automation engineer, Software company
"It's almost scary how accurate it is."
I wrote just a couple of sentences and Touchstone knew the whole application. Honestly, I was pretty impressed with how quickly it got there.
- Tester, IP and research data company
"It won't just assume success and carry on blithely."
I really approve of this. You've clearly built in the right guardrails, so it checks its results instead of assuming everything worked.
- Testing lead, Global engineering consultancy
"It would actually help my testers not over-test."
It's de-scoped the declines. It's not testing the whole decline flow, only that you can change a decision, which is exactly right. Really accurate.
- Test lead, Financial services group
What Our Beta Customers Say About Touchstone
"It's something a human would do, not a tool."
Late deliveries made in-sprint automation a struggle. Now we upload requirements early and have everything ready when the feature lands.
- Test automation engineer, Global insurer
"Almost 15 out of 10."
Our material isn't well organised. It makes sense to us, but I'm impressed by how Touchstone made sense of all of it and fit it into this template. Very Impressive.
- QA and delivery lead, Global IT services provider
"I wouldn't say it's left any big gaping holes."
Comparing the PDF I provided with what came out, I think it's really good. It's exciting to see it take a PDF without much information.
- Automation engineer, Software company
"It's almost scary how accurate it is."
I wrote just a couple of sentences and Touchstone knew the whole application. Honestly, I was pretty impressed with how quickly it got there.
- Tester, IP and research data company
"It won't just assume success and carry on blithely."
I really approve of this. You've clearly built in the right guardrails, so it checks its results instead of assuming everything worked.
- Testing lead, Global engineering consultancy
"It would actually help my testers not over-test."
It's de-scoped the declines. It's not testing the whole decline flow, only that you can change a decision, which is exactly right. Really accurate.
- Test lead, Financial services group
What the Release Evidence Contains
Trace each requirement back to its source, each journey back to its requirement and each execution back to the coverage it verified. Query the complete chain directly, with no manual reconstruction.
Every proposal, approval, rejection and repair is attributed to a person, with everything that change touched linked in the same history, so a decision can be traced back long after it was made.
Any two versions of a requirement or journey compare side by side. Nothing is overwritten and every earlier version stays recoverable, so a change can be reviewed against what it replaced.
Every flag, proposal and result links to the exact review surface, fan-outs collapse into digests rather than notification storms, and pending decisions sit in one list.
What the Release Evidence Contains
Trace each requirement back to its source, each journey back to its requirement and each execution back to the coverage it verified. Query the complete chain directly, with no manual reconstruction.
Every proposal, approval, rejection and repair is attributed to a person, with everything that change touched linked in the same history, so a decision can be traced back long after it was made.
Any two versions of a requirement or journey compare side by side. Nothing is overwritten and every earlier version stays recoverable, so a change can be reviewed against what it replaced.
Every flag, proposal and result links to the exact review surface, fan-outs collapse into digests rather than notification storms, and pending decisions sit in one list.
What the Release Evidence Contains
Trace each requirement back to its source, each journey back to its requirement and each execution back to the coverage it verified. Query the complete chain directly, with no manual reconstruction.
Every proposal, approval, rejection and repair is attributed to a person, with everything that change touched linked in the same history, so a decision can be traced back long after it was made.
Any two versions of a requirement or journey compare side by side. Nothing is overwritten and every earlier version stays recoverable, so a change can be reviewed against what it replaced.
Every flag, proposal and result links to the exact review surface, fan-outs collapse into digests rather than notification storms, and pending decisions sit in one list.
What the Release Evidence Contains
Trace each requirement back to its source, each journey back to its requirement and each execution back to the coverage it verified. Query the complete chain directly, with no manual reconstruction.
Every proposal, approval, rejection and repair is attributed to a person, with everything that change touched linked in the same history, so a decision can be traced back long after it was made.
Any two versions of a requirement or journey compare side by side. Nothing is overwritten and every earlier version stays recoverable, so a change can be reviewed against what it replaced.
Every flag, proposal and result links to the exact review surface, fan-outs collapse into digests rather than notification storms, and pending decisions sit in one list.
What the Evidence Becomes Over Time
Every decision your team makes inside the loop is evidenced, meaning what was approved, what was repaired, what was rejected and why. Over the coming releases that record becomes intelligence. Autonomous QA Intelligence will learn your application's intent, execution history and change patterns, and take on more of the QA decision over time, under the same governance rather than beyond it. The loop you run today is what earns it.
What the Evidence Becomes Over Time
Every decision your team makes inside the loop is evidenced, meaning what was approved, what was repaired, what was rejected and why. Over the coming releases that record becomes intelligence. Autonomous QA Intelligence will learn your application's intent, execution history and change patterns, and take on more of the QA decision over time, under the same governance rather than beyond it. The loop you run today is what earns it.
What the Evidence Becomes Over Time
Every decision your team makes inside the loop is evidenced, meaning what was approved, what was repaired, what was rejected and why. Over the coming releases that record becomes intelligence. Autonomous QA Intelligence will learn your application's intent, execution history and change patterns, and take on more of the QA decision over time, under the same governance rather than beyond it. The loop you run today is what earns it.
Where Touchstone Draws the Line
Boundaries worth stating before an evaluation rather than during one.
It is not hands-off
Every change passes a human gate by design. If you want ungoverned autonomy with nobody accountable, this is the wrong platform.
It does not read everything at once
Retrieval is semantic, so agents pull the most relevant sources for each task rather than re-reading your entire repository on every generation. Very large documents work best split into their natural sections.
It shows its misses
The Autopilot's reasoning is visible while it authors, including the attempts that fail validation. You watch it work rather than seeing only the result.
It does not test what a browser cannot reach
Browser-based surfaces and the API and data layers behind them are in scope. Thick desktop clients, terminal applications and native mobile are not, and that boundary is worth establishing early in a programme.
Where Touchstone Draws the Line
Boundaries worth stating before an evaluation rather than during one.
It is not hands-off
Every change passes a human gate by design. If you want ungoverned autonomy with nobody accountable, this is the wrong platform.
It does not read everything at once
Retrieval is semantic, so agents pull the most relevant sources for each task rather than re-reading your entire repository on every generation. Very large documents work best split into their natural sections.
It shows its misses
The Autopilot's reasoning is visible while it authors, including the attempts that fail validation. You watch it work rather than seeing only the result.
It does not test what a browser cannot reach
Browser-based surfaces and the API and data layers behind them are in scope. Thick desktop clients, terminal applications and native mobile are not, and that boundary is worth establishing early in a programme.
Where Touchstone Draws the Line
Boundaries worth stating before an evaluation rather than during one.
It is not hands-off
Every change passes a human gate by design. If you want ungoverned autonomy with nobody accountable, this is the wrong platform.
It does not read everything at once
Retrieval is semantic, so agents pull the most relevant sources for each task rather than re-reading your entire repository on every generation. Very large documents work best split into their natural sections.
It shows its misses
The Autopilot's reasoning is visible while it authors, including the attempts that fail validation. You watch it work rather than seeing only the result.
It does not test what a browser cannot reach
Browser-based surfaces and the API and data layers behind them are in scope. Thick desktop clients, terminal applications and native mobile are not, and that boundary is worth establishing early in a programme.
Where Touchstone Draws the Line
Boundaries worth stating before an evaluation rather than during one.
It is not hands-off
Every change passes a human gate by design. If you want ungoverned autonomy with nobody accountable, this is the wrong platform.
It does not read everything at once
Retrieval is semantic, so agents pull the most relevant sources for each task rather than re-reading your entire repository on every generation. Very large documents work best split into their natural sections.
It shows its misses
The Autopilot's reasoning is visible while it authors, including the attempts that fail validation. You watch it work rather than seeing only the result.
It does not test what a browser cannot reach
Browser-based surfaces and the API and data layers behind them are in scope. Thick desktop clients, terminal applications and native mobile are not, and that boundary is worth establishing early in a programme.
AI-native, proven in production.
10x
Faster execution
9x
Faster authoring
85%
Less maintenance
50%
Lower QA cost
AI-native, proven in production.
10x
Faster execution
9x
Faster authoring
85%
Less maintenance
50%
Lower QA cost
AI-native, proven in production.
10x
Faster execution
9x
Faster authoring
85%
Less maintenance
50%
Lower QA cost
Proven where quality and accountability matter
Recognised by independent analysts, trusted by enterprise teams, and built with the security controls required for critical software.
WAVE STRONG PERFORMER
Proven where quality and accountability matter
Recognised by independent analysts, trusted by enterprise teams, and built with the security controls required for critical software.
WAVE STRONG PERFORMER
Proven where quality and accountability matter
Recognised by independent analysts, trusted by enterprise teams, and built with the security controls required for critical software.
WAVE STRONG PERFORMER
Frequently Asked Questions
How Touchstone works in practice, from what each agent produces to what your team still approves.
What is Touchstone?
What do the three Touchstone agents do?
What happens when a specification changes?
Does test execution depend on the AI?
What does the evidence include?
Frequently Asked Questions
How Touchstone works in practice, from what each agent produces to what your team still approves.
What is Touchstone?
What do the three Touchstone agents do?
What happens when a specification changes?
Does test execution depend on the AI?
What does the evidence include?
Frequently Asked Questions
How Touchstone works in practice, from what each agent produces to what your team still approves.
What is Touchstone?
What do the three Touchstone agents do?
What happens when a specification changes?
Does test execution depend on the AI?
What does the evidence include?
See what your next release looks like with Virtuoso
Book a walkthrough on your applications and your workflows. Bring a requirement, a user journey, or a brittle Selenium script, and watch the loop run on something you recognise.
See what your next release looks like with Virtuoso
Book a walkthrough on your applications and your workflows. Bring a requirement, a user journey, or a brittle Selenium script, and watch the loop run on something you recognise.
See what your next release looks like with Virtuoso
Book a walkthrough on your applications and your workflows. Bring a requirement, a user journey, or a brittle Selenium script, and watch the loop run on something you recognise.
Trust Center
AICPA
SOC
WAVE STRONG PERFORMER
@ Copyright 2026 SpotQA, Creators of Virtuoso QA
Trust Center
AICPA
SOC
WAVE STRONG PERFORMER
@ Copyright 2026 SpotQA, Creators of Virtuoso QA
Trust Center
AICPA
SOC
WAVE STRONG PERFORMER
@ Copyright 2026 SpotQA, Creators of Virtuoso QA