This publish is co-written with Moshiko Ben Abu, Software program Engineer at CyberArk.
CyberArk achieved as much as 95% discount in case decision time utilizing Amazon Bedrock and Apache Iceberg.
This enchancment addresses a problem in technical help workflow: when a help engineer receives a brand new buyer case, the largest bottleneck is commonly not diagnosing the issue however making ready the information. Buyer logs arrive in several codecs from a number of distributors, and every new log format usually requires handbook integration and correlation earlier than an investigation can start. For easy circumstances, this course of can take hours. For extra complicated investigations, it may well take days, slowing decision and decreasing total engineer productiveness.
CyberArk is a worldwide chief in id safety. Centered on clever privilege controls, it gives complete safety for human, machine, and AI identities throughout enterprise purposes, distributed workforces, and hybrid cloud environments.
On this publish, we present you ways CyberArk redesigned their help operations by combining Iceberg’s clever metadata administration with AI-powered automation from Amazon Bedrock. You’ll learn to simplify knowledge processing flows, automate log parsing for various codecs, and construct autonomous investigation workflows that scale robotically.
To realize these outcomes, CyberArk wanted an answer that might ingest buyer logs, robotically construction them, set up relationships between associated occasions, and make every little thing queryable in minutes, not days. The structure needed to be serverless to deal with unpredictable help volumes, safe sufficient to guard buyer Personally Identifiable Info (PII), and quick sufficient to permit identical day case decision.
The legacy structure: Bottlenecks and handbook workflows
When help engineers obtained buyer circumstances, they’d add log information to the information lake saved in Amazon Easy Storage Service (Amazon S3). The unique design then suffered from the complexity of multi-step uncooked knowledge processing.
First, CyberArk’s customized parsing logic working on AWS Fargate would parse these uploaded log information and rework the uncooked knowledge. Throughout this stage, the system additionally needed to scan for PII and masks delicate knowledge to guard buyer privateness.
Subsequent, a separate course of transformed the processed knowledge into Parquet format.
Lastly, AWS Glue crawlers have been required to find new partitions and replace desk metadata for processed Parquet information. This dependency grew to become probably the most complicated and time-consuming a part of the pipeline. Crawlers ran as asynchronous batch jobs quite than in actual time, typically introducing delays of minutes to hours earlier than help engineers may question the information.
However the inefficiency went deeper than simply architectural complexity. CyberArk helps clients working various product environments throughout a number of distributors. Every vendor and product produces logs in several codecs with distinctive schemas, discipline names, and constructions. Including help for a brand new vendor meant days of integration work to know their log format and construct customized parsers.
Determine 1: Legacy log ingestion structure diagram exhibiting the stream from S3 add by AWS Fargate processing with AWS Glue Crawler
Past ingestion, the investigation course of itself was handbook and time consuming. Assist engineers would manually question knowledge, correlate occasions throughout totally different log sources, search by product documentation, and piece collectively root trigger evaluation by trial and error. This course of required deep product experience and will take hours or days relying on situation complexity. The brand new structure addresses these inefficiencies by three key improvements:
- Single stage serverless processing: AWS Fargate with PyIceberg straight creates Iceberg tables from uncooked logs in a single cross, eradicating intermediate processing steps and crawler dependencies totally.
- AI powered dynamic parsing: Amazon Bedrock robotically generates grok patterns for log parsing by analyzing file schemas, remodeling what was as soon as a handbook, time consuming course of into a completely automated workflow.
- Autonomous investigation with AI Brokers: AI Brokers autonomously carry out full root trigger evaluation by querying log knowledge, analyzing product data bases, figuring out occasion flows, and recommending options, remodeling hours of handbook investigation into minutes of automated intelligence.
The answer: AI-powered automation meets single-stage Iceberg processing
The brand new system delivers zero contact log processing from add to question. Assist engineers merely add buyer log ZIP information to the system. Right here’s the place the transformation occurs: CyberArk’s customized processing logic nonetheless runs on AWS Fargate, however now it makes use of Amazon Bedrock to intelligently perceive the information.
Zero-touch log processing workflow
The system extracts pattern log entries from the uploaded log information and sends them to Amazon Bedrock together with context in regards to the log supply and desk schema from AWS Glue Information Catalog. Amazon Bedrock analyzes the samples, understands the construction, and robotically generates grok patterns optimized for the particular log format.
Grok patterns are structured expressions that outline learn how to extract significant fields from unstructured log textual content. For instance, the next grok sample specifies {that a} timestamp seems first, adopted by a severity degree, then a message physique %{TIMESTAMP_ISO8601:timestamp} %{LOGLEVEL:severity} %{GREEDYDATA:message}
The system validates these grok patterns in opposition to further samples to confirm accuracy earlier than making use of them to parse the entire log file. Efficiently validated grok patterns are saved in Amazon DynamoDB, making a repository of recognized patterns. When the system encounters comparable log codecs in future uploads, it may well retrieve these patterns straight from Amazon DynamoDB, avoiding redundant grok sample technology. Amazon Bedrock processes log samples in real-time with out retaining buyer knowledge or utilizing it for mannequin coaching, sustaining knowledge privateness.
This whole course of invokes Claude 3.7 Sonnet mannequin from Amazon Bedrock and is orchestrated by AWS Fargate duties with retry logic for reliability. The processing makes use of these AI-generated grok patterns to parse the logs and create or replace Iceberg tables utilizing PyIceberg APIs with out human intervention.
This automation diminished logs onboarding time from days to minutes, enabling CyberArk to deal with various buyer environments with out handbook intervention.
Determine 2: Log ingestion structure diagram exhibiting the stream from S3 add by AWS Fargate processing with Amazon Bedrock integration to Iceberg desk creation
Apache Iceberg: Simplified structure, sooner queries
Iceberg simplified and improved CyberArk’s knowledge lake structure by addressing the 2 major bottlenecks within the legacy system: sluggish schema administration and inefficient question efficiency.
Constructed-in schema evolution removes crawler dependency
Within the legacy structure, AWS Glue crawlers grew to become a supply of operational overhead and latency. Even when triggered on demand, crawlers ran as batch jobs over S3 prefixes to find partitions and replace metadata. As knowledge volumes grew and datasets diversified throughout distributors and schemas, groups needed to handle and function a rising variety of crawler jobs. The ensuing delays, typically starting from minutes to hours, slowed knowledge availability and downstream investigation workflows.
Iceberg removes this whole layer of complexity. Iceberg’s clever metadata layer robotically tracks desk construction, schema modifications, and partition data as knowledge is written. When CyberArk’s processing creates or updates Iceberg tables by PyIceberg, the metadata is up to date immediately and atomically. There’s no ready for crawlers jobs to finish, and no danger of stale metadata. The second knowledge is written, it’s instantly queryable in Amazon Athena.
PyIceberg: Making Iceberg accessible past Apache Spark
Working with Iceberg normally concerned Apache Spark and the complexity of distributed knowledge processing. PyIceberg modified that by letting CyberArk create and handle Iceberg tables utilizing a easy Python library. CyberArk’s knowledge engineers may write simple Python code working on AWS Fargate to create Iceberg tables straight from parsed logs, with out spinning up Spark clusters.
This accessibility was important for CyberArk’s serverless structure. PyIceberg enabled single stage processing the place AWS Fargate duties may parse logs, apply PII masking, and create Iceberg tables in a single cross. The end result was easier code and decrease operational overhead.
Metadata-driven question optimization delivers velocity
Along with eradicating crawlers, Iceberg considerably improved question efficiency by its clever metadata structure. Iceberg maintains detailed statistics about knowledge information, together with min/max values, null counts, and partition data. When help engineers question knowledge in Athena, Iceberg’s metadata layer helps partition pruning and file skipping, ensuring queries solely learn the particular information containing related knowledge. For CyberArk’s use case, the place tables are partitioned by case ID, this implies a question for a particular help case solely reads the information for that case, ignoring probably hundreds of irrelevant information. This metadata pushed optimization diminished question execution time from minutes to seconds, permitting help engineers to interactively discover knowledge quite than ready for outcomes.
ACID transactions keep knowledge consistency
In a multi consumer help setting the place a number of engineers could also be analyzing overlapping circumstances or importing logs concurrently, knowledge consistency is crucial. Iceberg’s ACID transaction help helps confirm that concurrent writes don’t corrupt knowledge or create inconsistent states. Every desk replace is atomic, remoted, and sturdy, offering the reliability CyberArk wanted for manufacturing help operations.
Time journey allows historic evaluation
Iceberg’s built-in versioning permits help engineers to question historic states of information, important for understanding how buyer points advanced over time. If an engineer must see what the logs appeared like when a case was first opened versus after a buyer utilized a patch, Iceberg’s time journey capabilities make this simple. This function proved important for complicated troubleshooting situations the place understanding the timeline of occasions was important to decision.
Automated desk optimization with AWS Glue
Iceberg tables require periodic upkeep to keep up question efficiency.
CyberArk enabled AWS Glue computerized desk optimization for his or her Iceberg tables, which handles compaction and expired snapshot cleanup within the background.
For CyberArk’s steady add workflow, this automation avoids efficiency degradation over time. Tables keep optimized with out handbook intervention from the engineering staff.
AI Brokers: Autonomous investigation workflow
Whereas the Claude 3.7 Sonnet mannequin from Amazon Bedrock automates grok sample technology for log ingestion, the extra superior use of Amazon Bedrock comes within the investigation workflow. We use AI brokers with Bedrock fashions to alter how help engineers analyze and resolve buyer points.
From handbook evaluation to AI powered investigation
Within the legacy workflow, help engineers would manually question knowledge, correlate occasions throughout totally different log sources, search by product documentation, and piece collectively root trigger evaluation by trial and error. This course of required deep product experience and will take hours or days relying on situation complexity. AI Brokers automate this whole investigation course of. Assist engineers use an inner portal to ask questions in pure language about buyer points, questions like
“Present me authentication errors for case 12345 within the final 24 hours”, “What have been the most typical errors throughout circumstances opened this week?” or “Evaluate the error patterns between case 12345 and case 12346.”
Behind the scenes, the system fires specialised AI Brokers that autonomously carry out thorough evaluation.
How help brokers work
Every AI Agent operates as an clever investigator with a transparent mission: perceive what occurred, decide why it occurred, and suggest learn how to repair it. When a help engineer asks a query, the agent collects related knowledge by querying Athena to retrieve log knowledge from Iceberg tables, filtering for the particular case and time interval related to the investigation. The agent then accesses CyberArk’s inner data base for the particular product concerned, understanding recognized points, frequent error patterns, and documented options. The agent then performs the next evaluation:
- Circulate identification: Analyzes the sequence of occasions within the logs to know what truly occurred in the course of the buyer’s situation
- Root trigger willpower: Correlates log occasions with product data to establish the underlying reason for the issue
- Resolution suggestions: Suggests particular remediation steps based mostly on the foundation trigger evaluation and recognized decision patterns
This whole course of occurs in minutes, delivering superior evaluation that might have taken help engineers hours to carry out manually.
For complicated circumstances the place an answer shouldn’t be discovered, the help agent escalates to a different, specialised agent that interacts with service engineers to gather further inputs and experience. This human-in-the-loop method makes certain that even probably the most difficult circumstances obtain acceptable consideration whereas nonetheless benefiting from the automated investigation workflow. The insights gathered from these escalated circumstances are robotically fed again into CyberArk’s data base, repeatedly enhancing the system’s capability to deal with comparable points autonomously sooner or later.
Amazon Bedrock by no means shares buyer knowledge with mannequin suppliers or makes use of it to coach basis fashions, case knowledge and investigation insights stay inside CyberArk’s setting.
Concurrent agent execution at scale
When a number of help engineers examine totally different circumstances concurrently, the answer runs specialised brokers concurrently. CyberArk at present makes use of Claude 3.7 Sonnet as the muse mannequin for these brokers. Every agent works independently on its assigned investigation, working in parallel with out useful resource competition. This concurrent execution permits the investigation workflow to scale robotically with help quantity, dealing with peak masses with out efficiency degradation.
AI-powered investigation benefit
This AI-powered investigation workflow delivers two key benefits.
Investigations that took hours now full in minutes, enabling help engineers to resolve as much as 4x extra circumstances per day.
The system additionally creates a steady studying suggestions loop. When circumstances require handbook decision by engineers, these resolutions are robotically recorded and fed again into the data base. Future investigations profit from this gathered experience, with brokers making use of classes discovered from earlier handbook resolutions to comparable circumstances. Amazon Bedrock doesn’t use buyer knowledge to coach basis fashions. Case knowledge and investigation insights stay inside CyberArk’s setting.
This automated suggestions mechanism means the investigation workflow turns into more practical over time, repeatedly enhancing decision accuracy and velocity.
Determine 3: Investigation workflow diagram exhibiting pure language question by AI Brokers to Athena queries and data base evaluation
Scaling with out proportional engineering development
The enterprise influence of this AI automation is critical. CyberArk can increase its vendor protection and product portfolio with out including knowledge engineering headcount. The identical system that handles at this time’s log sorts will robotically deal with tomorrow’s additions, whether or not that’s ten new codecs or hundreds, considerably decreasing time to marketplace for new product and vendor integrations.
The outcomes: Important enhancements in decision time and productiveness
The transformation delivered measurable enhancements throughout each key metric.
Decision time: CyberArk achieved as much as 95% discount in time from case task to decision. Easy circumstances that used to take 4 to six hours now take simply 15 to half-hour. Advanced circumstances that beforehand took as much as 15 days at the moment are accomplished in 2 to 4 hours.
Engineer productiveness: Assist engineers now deal with 8 to 12 circumstances per day, in comparison with simply 2 to three circumstances earlier than. This implies every engineer helps as much as 4x extra clients.
Information availability: Logs are queryable inside minutes of add as a substitute of ready hours or days. Assist engineers can begin investigating points virtually instantly after receiving buyer knowledge.
Operational effectivity: The system requires zero handbook intervention for brand new log codecs or schema modifications. Instances that used to require days of information engineering work now occur robotically.
Value optimization: The serverless structure alleviated idle infrastructure prices whereas scaling robotically with demand. CyberArk solely pays for what they use, after they use it.
Buyer satisfaction: Quicker decision instances and proactive situation identification considerably improved the client expertise. Issues get solved in hours as a substitute of days, and clients spend much less time ready for solutions.
What’s subsequent?
Whereas AWS continues to innovate throughout each knowledge lake administration and agentic AI infrastructure, the next capabilities align properly with CyberArk’s structure and will supply further operational advantages because the system scale.
Agent infrastructure maturity
Because the agent-based structure scales to deal with hundreds of concurrent investigations, CyberArk is transitioning to Amazon Bedrock AgentCore for future agent deployments. AgentCore gives a managed runtime for manufacturing AI brokers with enhanced observability by AWS X-Ray integration, clever reminiscence for context retention throughout classes, and streamlined operational workflows. Whereas the present AI Brokers implementation delivers the efficiency and reliability CyberArk wants at this time, AgentCore represents a pure evolution path as operational necessities develop, providing framework-agnostic deployment, computerized scaling, and complete monitoring capabilities with out infrastructure administration overhead.
Amazon S3 Tables
CyberArk’s present structure makes use of Iceberg tables saved in Amazon S3 buckets. Amazon S3 Tables presents absolutely managed Iceberg tables with built-in optimization.
As CyberArk proceed to scale with lots of of Iceberg tables and speedy knowledge development, CyberArk is exploring a migration to Amazon S3 Tables to additional scale back operational overhead.
S3 Tables take away the necessity to arrange and monitor AWS Glue upkeep jobs. It robotically performs upkeep to reinforce the efficiency of Iceberg tables, together with unreferenced file removing, file compaction, and snapshot administration. Moreover, S3 Tables gives Clever-Tiering that robotically strikes knowledge between storage courses based mostly on entry patterns, optimizing storage prices with out handbook intervention.
As a result of S3 Tables makes use of Iceberg open desk format, migration wouldn’t require modifications to current Athena queries and PyIceberg code. This flexibility permits CyberArk to guage and undertake S3 Tables when the operational and value advantages align with their enterprise wants.
Conclusion
CyberArk’s transformation demonstrates how combining fashionable knowledge lake structure with AI automation can considerably change operational economics. By combining Iceberg’s clever metadata administration with AI-powered automation from Amazon Bedrock, CyberArk remodeled case decision from days to minutes whereas enabling help operations to scale robotically with enterprise development. Assist engineers now spend their time fixing buyer issues as a substitute of wrangling knowledge, clients obtain sooner resolutions, and the system scales robotically with the enterprise.
To study extra about Iceberg on AWS, consult with Working with Amazon S3 Tables and desk buckets and Utilizing Apache Iceberg on AWS. To study extra about Amazon Bedrock AgentCore, consult with Amazon Bedrock AgentCore.
In regards to the authors